pp-game-goat

Game GOAT — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the game-goat-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:
```
npx -y @mvanhorn/printing-press-library install game-goat --cli-only
```
Verify: game-goat-pp-cli --version
Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill.

If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead:

go install github.com/mvanhorn/printing-press-library/library/media-and-entertainment/game-goat/cmd/game-goat-pp-cli@latest

If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.

What this CLI covers

350,000+ games across 50 platforms via RAWG (Video Games Database) (tags, genres, developers, publishers, creators, Metacritic scores, store links).
Keyless Steam enrichment: review scores and player counts joined into rating cards.
Remake-aware title resolution: shared names (DOOM 1993 vs 2016, franchise shorthand like "halo") resolve with a notice on stderr and meta.ambiguous in JSON; pin with --year or a RAWG id.
One free RAWG API key powers live commands (see Auth Setup); local search over synced data works offline.
IsThereAnyDeal historical and current price tracking (needs ITAD_API_KEY): all-time / 1-year / 3-month lows, a dated change log, and per-storefront current prices, localised to a --country currency.

Terms of Use

Free for personal use as long as you attribute RAWG as the source of the data and/or images and add an active hyperlink from every page where the data of RAWG is used.
Free for commercial use for startups and hobby projects with not more than 100,000 monthly active users or 500,000 page views per month. If your project is larger than that, email us at api@rawg.io for commercial terms.
No cloning. It would not be cool if you used our API to launch a clone of RAWG. We know it is not always easy to say what is a duplicate and what isn't. Drop us a line at api@rawg.io if you are in doubt, and we will talk it through.
You must include an API key with every request. The key can be obtained at https://rawg.io/apidocs. If you don’t provide it, we may ban your requests.

Read more.

When Not to Use This CLI

Do not activate this CLI for requests that require creating, updating, deleting, publishing, commenting, upvoting, inviting, ordering, sending messages, booking, purchasing, or changing remote state. Also do not use it for game news, esports schedules, purchasing or checkout, or running/emulating games — RAWG (Video Games Database) exposes none of these, and this CLI never buys anything. It does read prices: price-history and prices pull historical and current storefront prices from IsThereAnyDeal (read-only, requires ITAD_API_KEY). This printed CLI exposes read-only commands against the API for inspection, export, sync, and analysis.

Unique Capabilities

These capabilities aren't available in any other tool for this API.

similar — Games like : the seed's own studio first, then its defining gameplay tag (roguelite, metroidvania) found by tag-neighborhood co-occurrence, then a confidence-floored genre join. Every row carries its tier and a reason.
retention — Community completion and drop verdict for one game from RAWG added_by_status counts (needs RAWG_API_KEY).
price-history — Historical price tracking for one game: all-time / 1-year / 3-month lows, the current best storefront price, a dated change log, and a buy-now verdict, localised to a --country currency (needs ITAD_API_KEY).
prices — Current prices across storefronts, cheapest first, with a --deals-only filter and the all-time low for context, localised to a --country currency (needs ITAD_API_KEY).
steam search — Plural keyless search of the Steam store across games, demos, DLC, soundtracks, software, video, mods, and hardware, with store tags, price, release date, platforms, and demo links on every row.
steam browse — Paginated Steam catalog browse filtered by app type, free-only, store tag, and coming-soon/released, localised with --country; "every free demo in my region" is one command.
steam demos — Demos only, each with the full game it belongs to: filter by --tag (every tag required, repeatable or comma-separated) or a single --title batch; released demos by default, --coming-soon for unreleased.

Command Reference

creator-roles — List and get creator roles

game-goat-pp-cli creator-roles — Get a list of creator positions (jobs).

creators — List and get creators

game-goat-pp-cli creators list — Get a list of game creators.
game-goat-pp-cli creators read — Get details of the creator.

developers — List and get developers

game-goat-pp-cli developers list — Get a list of game developers.
game-goat-pp-cli developers read — Get details of the developer.

games — List and get games

game-goat-pp-cli games list — Get a list of games.
game-goat-pp-cli games read — Get details of the game.

genres — List and get genres

game-goat-pp-cli genres list — Get a list of video game genres.
game-goat-pp-cli genres read — Get details of the genre.

platforms — List and get platforms

game-goat-pp-cli platforms list — Get a list of video game platforms.
game-goat-pp-cli platforms lists-parents-list — For instance, for PS2 and PS4 the “parent platform” is PlayStation.
game-goat-pp-cli platforms read — Get details of the platform.

publishers — List and get publishers

game-goat-pp-cli publishers list — Get a list of video game publishers.
game-goat-pp-cli publishers read — Get details of the publisher.

stores — List and get stores

game-goat-pp-cli stores list — Get a list of video game storefronts.
game-goat-pp-cli stores read — Get details of the store.

tags — List and get tags

game-goat-pp-cli tags list — Get a list of tags.
game-goat-pp-cli tags read — Get details of the tag.

games — discovery and detail

game-goat-pp-cli games search — live title search with remake-aware ambiguity notices.
game-goat-pp-cli games get — full game detail by title or RAWG id.
game-goat-pp-cli games popular — most-added games feed.
game-goat-pp-cli games top-rated — highest-rated games feed.
game-goat-pp-cli games upcoming — releases in the next 90 days.
game-goat-pp-cli discover — RAWG's filter surface (genres, tags, platforms, stores, dates, ordering, metacritic).

ratings · retention · series · similar

game-goat-pp-cli ratings <title> — RAWG + Metacritic + Steam rating card (title or bare RAWG id).
game-goat-pp-cli retention <title> — community beaten/dropped/playing/yet split with an aspirational-trap verdict (needs RAWG_API_KEY).
game-goat-pp-cli series <title> — franchise play order by release date, anchor included (title or bare RAWG id).
game-goat-pp-cli similar <title> — tiered recommendations: same studio (capped), defining gameplay tag, then shared genres; each row carries tier and reason (title or bare RAWG id).

prices — IsThereAnyDeal history and storefront prices

game-goat-pp-cli price-history <title> — all-time / 1-year / 3-month lows, the current best price, a dated change log, and a buy-now verdict; prices localised by --country (needs ITAD_API_KEY).
game-goat-pp-cli prices <title> — current prices across storefronts, cheapest first, with --deals-only and --limit; localised by --country (needs ITAD_API_KEY).

framework

sync, search, analytics — local SQLite mirror and offline search; tail polls the live API; export streams live API data to a file.
which, workflow, api, agent-context, profile, feedback, doctor — agent-native plumbing.

steam — Keyless Steam store catalog: search, app records, filtered browse

game-goat-pp-cli steam search <term> — Search the Steam store catalog for games, demos, DLC, soundtracks, and more.
game-goat-pp-cli steam app <appid|title> — One full typed Steam store record, including demo links and the review summary.
game-goat-pp-cli steam browse — Paginated Steam catalog browse with type, free, tag, and release filters.
game-goat-pp-cli steam demos — Demos-only listing with the full game each demo belongs to; released by default, filter by --tag (every tag required) or one --title batch.

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

game-goat-pp-cli which "<capability in your own words>"

which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match — fall back to --help or use a narrower query. --json (and other machine formats) keep that exit-2 contract and write {"matches":[]} on stdout so agents can inspect the envelope without treating a miss as success.

Recipes

Games like one you loved

game-goat-pp-cli similar "Megabonk" --json --select results.name,results.tier,results.reason

Play a franchise in order

game-goat-pp-cli series "zelda" --json

Pin a remake when titles collide

game-goat-pp-cli ratings "resident evil 4" --year 2023 --json

A pinned --year is a hard constraint on the title too: if no game with that exact title was released in that year, the command reports not-found (drop --year or pass a RAWG id) rather than resolving a different game from the same year.

Will people actually finish it?

game-goat-pp-cli retention "elden ring" --json

Is now the cheapest it has ever been?

game-goat-pp-cli price-history "elden ring" --json

Historical lows (all-time, 1 year, 3 months), the current best storefront price, and a dated change log. Prices are localised to --country (ISO 3166-1 alpha-2; default ITAD_COUNTRY or US), so --country GB returns GBP. Requires an IsThereAnyDeal key — the ITAD_API_KEY env var or one stored via auth set-token --provider itad; get a free key at https://isthereanydeal.com/apps/.

What does it cost where I live?

game-goat-pp-cli prices "elden ring" --country GB --deals-only --json

Current price at every storefront, cheapest first, plus the all-time low for context. --deals-only keeps just active discounts; --limit caps the rows.

Search the Steam store

game-goat-pp-cli steam search "hollow knight" --json --select results.name,results.price,results.release_date

The keyless store search returns typed records: app type, release date, platforms, store tags, price, and the app's own demo links. --type takes a comma-separated list (game, demo, dlc, soundtrack, software, video, mod, hardware) and --limit goes up to 100. Text search has no second page — Valve's search service ignores an offset — so use steam browse when you need to page.

Every free demo in my region

game-goat-pp-cli steam browse --type demo --free --country DE --page 2 --agent

Filtered catalog browse with real pagination: --type, --free, --tag <name|tagid> (repeat it or comma-separate; every tag is required), and --coming-soon/--released. meta carries total, page, limit, and next_page. Free-to-play and early access are attributes of a record rather than app types, so --free is how you ask for them.

Find a demo by tag or title

game-goat-pp-cli steam demos --tag Roguelike --limit 20 --agent
game-goat-pp-cli steam demos --title portal --agent

steam demos is demos only: it fixes the app type to demo and never returns full games, and every row carries parent_app_id, parent_name, and parent_tags (the full game's store tag names, in Steam's order) for the full game it belongs to. The tags shown are the full game's: demos rarely carry tags of their own, so a demo's own tags appear as tags only when Steam lists any, and the human table's "full game tags" column shows the first three parent_tags. A bare steam demos lists the first page. Free-to-play titles are not demos, so use steam browse --free for those. Both paths return released demos ("available now") by default; --coming-soon swaps that for unreleased demos only, applied server-side so meta.total is the service's matching count. --tag <name|tagid> requires every tag (repeat it or comma-separate), and --title is a single search batch that defaults to 100 results (--limit up to 1000) and reports meta.truncated instead of a page cursor — --page is rejected with --title.

Request budget per invocation (unchanged): a browse page costs 3 requests (one catalog query, one tag-name dictionary lookup, and one lookup for the full-game names AND tags of every parent on the page); the tag-name dictionary is fetched once and shared with --tag resolution and the parent lookup, so adding --tag adds no request; a --title batch costs 1 search request, 1 tag-dictionary request, plus one full-game name+tag lookup per 200 games.

steam app always carries a has_demo boolean, and ratings adds has_demo and demo_app_ids when Steam resolves the game's appid. discover and similar can annotate every result with has_demo and demo_app_ids too, opt-in via --with-demos, which costs 1 extra RAWG request per result for its Steam store link plus 1 Steam request per 200 games.

The full Steam data-source note (which endpoints are used, why STEAM_API_KEY is not needed, and the bundle limitation) is the "Steam data sources" section of the README.

Auth Setup

Run game-goat-pp-cli auth setup to print the URL and steps for getting a key (add --launch to open the URL). Then set:

export RAWG_API_KEY="<your-key>"

To persist credentials, use echo "$TOKEN" | game-goat-pp-cli auth set-token. Stored secrets live in credentials.toml under the data dir, not in config.toml.

The steam commands need no key at all: they use Valve's keyless store services. STEAM_API_KEY is not used anywhere in this CLI; the key-gated Steam Web API (players, achievements, stats) is the separate steam-web CLI.

IsThereAnyDeal price data (optional)

price-history and prices read from IsThereAnyDeal and need their own free API key, independent of the RAWG key. Store it once (recommended) or export it per shell:

echo "$ITAD_API_KEY" | game-goat-pp-cli auth set-token --provider itad   # writes credentials.toml (0600)
# or: export ITAD_API_KEY="<your-key>"

Create a key at https://isthereanydeal.com/apps/. Prices are returned in the currency of the selected storefront country: pass --country <ISO-3166-1> (e.g. GB, DE) or set ITAD_COUNTRY for a default; without either, US/USD is used. A missing key surfaces as exit code 4 with setup guidance, not an upstream error.

Run game-goat-pp-cli doctor to verify setup.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color.

Global format flags share one contract on promoted, novel, sync, and --deliver paths:

--json — one JSON document on stdout (sync progress events go to stderr)
--compact — keep identity/status/timestamp fields; does not change the document vs stream shape
--csv / --plain — tabular rows (collection envelopes unwrap to the row array)
--quiet — one identity value per row, no envelope
Pipeable — JSON on stdout, errors on stderr
Filterable — --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:
```
game-goat-pp-cli creator-roles --agent --select id,name,slug
```
Previewable — --dry-run shows the request without sending
Offline-friendly — sync/search commands can use the local SQLite store when available
Non-interactive — never prompts, every input is a flag
Read-only — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests

Response envelope

Commands that read from the local store or the API wrap output in a provenance envelope:

{
  "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
  "results": <data>
}

Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal AND no machine-format flag (--json, --csv, --compact, --quiet, --plain, --select) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout.

Paths and state

Agents should treat the CLI's path resolver as part of the runtime contract:

Use --home <dir> for one invocation, or set GAME_GOAT_HOME=<dir> to relocate all four path kinds under one root.
Use per-kind env vars only when a specific kind must diverge: GAME_GOAT_CONFIG_DIR, GAME_GOAT_DATA_DIR, GAME_GOAT_STATE_DIR, GAME_GOAT_CACHE_DIR.
Resolution order is per-kind env var, --home, GAME_GOAT_HOME, XDG (XDG_CONFIG_HOME, XDG_DATA_HOME, XDG_STATE_HOME, XDG_CACHE_HOME), then platform defaults.
config contains settings like config.toml and profiles. data contains credentials.toml, data.db, cookies, and auth sidecars. state contains persisted queries, jobs, and teach.log. cache contains regenerable HTTP/cache files.
Stored secrets live in credentials.toml under the data dir. Existing legacy config.toml secrets are read for compatibility and leave config.toml on the first auth write.
Run game-goat-pp-cli doctor --fail-on warn to surface path and credential-location warnings. agent-context exposes a schema v4 paths block for agents that need the resolved dirs.

For MCP, pass relocation through the MCP host config. The MCP binary does not inherit CLI flags:

{
  "mcpServers": {
    "game-goat": {
      "command": "game-goat-pp-mcp",
      "env": {
        "GAME_GOAT_HOME": "/srv/game-goat"
      }
    }
  }
}

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use GAME_GOAT_HOME or per-kind vars as durable fleet levers, and use --home only for a single invocation. Relocation is not reversible by unsetting env vars; move files manually before clearing GAME_GOAT_HOME, or doctor will not find credentials left under the former root.

Automatic learning

This CLI ships a self-capturing learning loop. The CLI does its own bookkeeping: every invocation is journaled locally, a failed flag followed by a corrected retry auto-derives a flag_alias candidate, and a teach on a query family without a playbook auto-synthesizes a playbook_candidate from the session's journal. Your job is judgment only: recall first, act on surfaced candidates, teach the final answer, playbook amend when you observe a correction. You never record failures by hand.

Step 1: `recall` before any discovery

Before list/search/drill commands on a new user question, pass the question as an argv or MCP tool argument to recall --agent. Do not interpolate user-controlled text into a shell command line.

Quoted recall "<question>" breaks on an apostrophe, which is ordinary English. A quoted heredoc breaks when a body line equals the delimiter, and that delimiter is published in these docs. Write the question with a non-shell file-writing tool, then read it back as data:

# Write the question verbatim with your file-writing tool (no shell involved).
# Command substitution on a file only ever yields data — the shell never
# parses the file's bytes as syntax.
QUERY=$(cat /path/to/question.txt)
game-goat-pp-cli recall "$QUERY" --agent

Prefer MCP: pass the question as the tool's query argument. "$QUERY" after a file read is argv-safe; putting the question itself in the command text is not.

The response envelope:

{
  "query": "...",
  "normalized": "<normalized form>",
  "query_entities": ["..."],
  "found": true | false,
  "match_score": 0.0,
  "results": [
    { "resource_id": "...", "resource_type": "...", "venue": "...",
      "confidence": 2, "entity_match": "exact|partial|unknown",
      "source": "taught|preseed|pattern", "warnings": ["..."] }
  ],
  "mismatches": [ /* only when --debug-mismatches */ ],
  "warnings": [ /* top-level */ ],
  "candidates": [
    { "id": 12, "class": "flag_alias | playbook_candidate",
      "summary": "...", "sightings": 3, "last_seen": "...",
      "rationale": "...",
      "next_action": ["<trial command>", "game-goat-pp-cli learnings confirm 12"] }
  ],
  "playbook": {
    "query_family": "...",
    "playbook": {
      "steps": [ { "cmd": "<command with {slot} substitution>", "purpose": "..." } ],
      "entity_slots": ["$ENTITY"],
      "expected_tool_calls": 3
    },
    "slots_resolved": { "$ENTITY": { "token": "<live token>", "canonical": "<canonical>" } },
    "notes": "<workarounds + gotchas for this query family>"
  },
  "notes": "<duplicate surface for non-playbook callers>"
}

Empty-store short-circuit: if the store has no learnings, playbooks, or candidates yet (recall finds nothing and learnings list and learnings candidates are both empty), skip recall for the rest of this session instead of taxing every query; resume recall-first once something has been taught.

Step 2: decision tree

Read candidates, playbook, notes, results[0], and warnings in that order:

if Candidates present (warnings include "candidates_present"):
    -> candidates are try-then-confirm, never facts. Follow each candidate's
       two-step next_action verbatim: run the trial command first, then run
       `learnings confirm <id>` only after the trial verified the behavior.
       Reject a wrong candidate with `learnings reject <id>`.
    -> NEVER re-teach something recall surfaced as a candidate; confirm or
       reject that candidate instead of teaching a duplicate.
    -> candidates ride alongside playbooks and resource hits, not instead of
       them; continue with the branches below after acting on them.

if Playbook present:
    -> READ Playbook.notes verbatim FIRST (workarounds + gotchas the CLI surface doesn't expose)
    -> replay Playbook.steps in order, substituting Playbook.slots_resolved entries
       for the entity slot tokens. If a step's slot is unresolved, fall back to
       discovery for that step only.
    -> the Playbook's expected_tool_calls is a budget; if you find yourself running
       materially more, record the divergence via `game-goat-pp-cli playbook amend`
       at end-of-session.

elif Notes present (no Playbook):
    -> read Notes verbatim before any discovery step; they carry known gotchas
       for this query family even when no structured choreography exists yet.

elif Found AND Results[0].EntityMatch == "exact" AND Results[0].Confidence >= 2:
    -> skip discovery; fetch live data for Results[*].ResourceID in parallel

elif Found AND Results[0].EntityMatch == "partial":
    -> candidate hint, NOT a hit; read the resource title to validate before trusting

elif (any row in Mismatches[] when --debug-mismatches was passed):
    -> treat as cold start; the stored learning is for a different entity
       (different canonical resolved from query_entities)

else:  // Found == false, no playbook, no notes
    -> cold start; run discovery normally; teach the answer afterward (Step 4).
       If the family has no playbook yet, that teach auto-synthesizes a
       playbook candidate from this session's journal - you do not need to
       record one by hand.

Playbook and Notes are orthogonal to the per-resource path. A recall response can carry both a Playbook AND a Results[] hit - use both: the Playbook tells you which choreography to run; the resource hits short-circuit specific steps. Default to skipping mismatches; pass --debug-mismatches only when investigating cold-start surprises.

Candidate judgment details: learnings confirm <id> prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. learnings reject <id> tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; game-goat-pp-cli learnings candidates lists the full open set.

Graceful degradation: if learnings confirm is an unknown command, you are driving an older binary - ignore the candidates guidance and follow the rest of the protocol.

Step 3: always read `warnings`

low_confidence: row exists at confidence<2. Treat as a hint, not a skip-discovery hit.
resource_not_in_store: the local store doesn't have the resource the learning points at. The match validator couldn't classify entities — direct-fetch and re-evaluate.
cross_alias_match (per-result): the row was taught under a different alias and matched the live query's canonical via entity_lookups (e.g., a "USA" teach satisfying a "United States" recall). Trust the resource_id.
similar_shape_different_entity:<canonical> (top-level): a structurally matching row exists but its canonical entity differs from the live query's. Treated as cold start; the warning carries the conflicting canonical as a hint, but the row is NOT promoted into Results.
ambiguous_alias (top-level): a single query entity resolved to multiple canonicals (e.g., "Cards" → Arizona Cardinals + St. Louis Cardinals). Surface the ambiguity from context before committing to a resource.
candidates_present (top-level): the envelope carries a candidates section. Handle it via the candidates branch in Step 2 before anything else.
lookup_refresh_available (top-level): an entity in the query has no lookup row yet, but synced data could provide one. Run game-goat-pp-cli sync to refresh entity lookups.
Top-level no_learnings_for_query_family: the table had no rows above the Jaccard floor. Pure cold start.

Step 4: `teach &` after finalizing your response - always

Teaching is unconditional. After resolving a query the store could not answer, background-teach the final resource mapping - no call-count threshold, no judging whether it was "worth" learning. The teach is the anchor of the loop: it triggers playbook synthesis for a family without a playbook, and same-referent phrasings fold into one family so near-duplicate teaches do not fragment the store. Fire it after assembling your user-facing response but BEFORE emitting it, with a shell & so the call returns immediately. Pass the query the same way as recall — argv/MCP, or file-then-$QUERY. Do not splice the question into the command text:

QUERY=$(cat /path/to/question.txt)
game-goat-pp-cli teach --query "$QUERY" --resource-type <type> --resource <id1> --resource <id2>
# (append shell `&` to background it)

Silent on success. Errors only land in teach.log under the resolved state dir. Teach the most specific resource - if the user asked a broad question and you walked through parent records to find the specific answer, teach the leaf id, not the parent. The CLI uses seeded entity_lookups for cross-alias resolution at recall time, so a teach under one alias (e.g., "Niners") satisfies future queries under another alias (e.g., "49ers", "San Francisco") automatically.

PII rule: teach the structural question with identifiers stripped - never include names, emails, phone numbers, account ids, or other personal identifiers in taught queries or notes. The CLI scans teach queries for obvious email/phone shapes and warns, but does not block; strip before teaching rather than relying on the warning.

Step 5: playbooks - optional flags, automatic synthesis

You do not need to decide whether a session "deserves" a playbook: a teach on a family without one auto-synthesizes a playbook_candidate from the session's journal, and the next session judges it via confirm/reject. Attach explicit playbook flags only when you already hold choreography worth recording verbatim - workarounds the CLI didn't surface (silently-dropped flags, undocumented params, pagination tricks, payload gotchas). Prefer the integrated one-call form - record the resource learning and the playbook in the same teach invocation:

# Common case: record both the resource learning AND the playbook in one call.
QUERY=$(cat /path/to/question.txt)
game-goat-pp-cli teach \
  --query "$QUERY" \
  --resource <id> \
  --playbook-file ~/playbooks/<shape>.json \
  --playbook-notes-file ~/playbooks/<shape>-notes.md
# (append shell `&` to background it)

# Alternate: playbook-only (no resource to record alongside).
QUERY=$(cat /path/to/question.txt)
game-goat-pp-cli teach-playbook \
  --query "$QUERY" \
  --playbook-file ~/playbooks/<shape>.json \
  --notes-file ~/playbooks/<shape>-notes.md

Playbook files are JSON with steps, entity_slots, expected_tool_calls. Notes files are markdown carrying the gotchas verbatim. File-free callers (MCP-only agents) pass the same content inline: --playbook-json and --playbook-notes on the integrated teach form, --playbook-json and --notes on teach-playbook. On the integrated teach form, the playbook flags are optional - omit them entirely for a resource-only teach. On the standalone teach-playbook form, at least one of the playbook and notes flags must be set; both empty is rejected. Playbooks are keyed on the structural query family (entities stripped) so a recipe taught from one entity-shaped query applies to every other query of the same shape, with slots_resolved binding the live query's canonical at recall time.

When you DO find a playbook on a future recall, treat it as ground truth: replay the steps with slots_resolved substitutions, skip the discovery that the choreography already documents, and read notes before any step.

Step 6: `playbook amend &` when your debug response identifies a correction

If your debug-protocol response identifies a concrete correction the notes or playbook should know — a workaround, an undocumented endpoint shape, a stale field name, observed schema drift, an empty-payload fallback — fire playbook amend BEFORE emitting your user-facing response. Same fire-and-forget posture as teach. Pass the query and note as argv/MCP arguments, or write each with a non-shell file tool and read them back (QUERY=$(cat ...), NOTE=$(cat ...)). Do not interpolate either string into the command text:

QUERY=$(cat /path/to/question.txt)
NOTE=$(cat /path/to/note.txt)
game-goat-pp-cli playbook amend \
  --query "$QUERY" \
  --add-note "$NOTE"
# (append shell `&` to background it)

What counts as worth amending: a behavior you OBSERVED this session that future-you would benefit from knowing. Examples worth amending:

A workaround for a CLI surface that silently drops or misorders a flag.
An undocumented endpoint shape (response wrapped in {meta, results}, payload nested two levels deeper than the docs claim).
Observed schema drift (a field renamed, an index that shifted between seasons, a category label that the API now returns lower-cased).

What does NOT belong in notes:

The year-specific or entity-specific answer to the user's question. That's the response, not a learning.
Per-team / per-athlete / per-row data the playbook already retrieves at runtime.
Statements that paraphrase what the existing notes already say.

The amend command appends to the family's existing notes with a timestamped marker ([amend YYYY-MM-DDTHH:MMZ]: <text>). Multiple amends accumulate; the audit trail is visible. If no playbook exists yet for the family, amend creates a notes-only one (so cold-start corrections still land).

PII discipline for amend notes

playbook amend notes are designed to potentially flow upstream as shared knowledge in future versions of the Printing Press. Keep them clean of user-identifying content so the upstream-contribution path stays open without retroactive scrubbing:

Do NOT embed paths to user filesystems, personal API keys or tokens, user email addresses, user GitHub handles, or specific query histories tied to a single user.
Acceptable: endpoint shapes, undocumented field names, API gotchas, observed schema drift, workarounds for CLI surfaces, generalizable pagination or retry tactics.

If a correction is only meaningful with user-specific context, it belongs in a personal note, not in the playbook amend.

Measuring the loop

game-goat-pp-cli learnings stats reports recall hit rate, teach-to-reuse, playbook resolution rate, and candidate confirm/reject counts from the local learn_events table. Rates are null until they have a denominator; everything stays on this machine. Use it to check whether the loop is earning its keep for this CLI.

Disabling learning

--no-learn on a single command short-circuits both recall and the teach write path. Use for deterministic agent flows or tests that must not be affected by accumulated learnings.
GAME_GOAT_NO_LEARN=true in the environment globally disables the pipeline.

Agent Feedback

When you (or the agent) notice something off about this CLI, record it:

game-goat-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
game-goat-pp-cli feedback --stdin < notes.txt
game-goat-pp-cli feedback list --json --limit 10

Entries are stored locally as feedback.jsonl under the resolved data dir. They are never POSTed unless GAME_GOAT_FEEDBACK_ENDPOINT is set AND either --send is passed or GAME_GOAT_FEEDBACK_AUTO_SEND=true. Default behavior is local-only.

Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.

Output Delivery

Every command accepts --deliver <sink>. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:

Sink	Effect
`stdout`	Default; write to stdout only
`file:<path>`	Atomically write output to `<path>` (tmp + rename). Binary-response commands write decoded payload bytes (not the base64 JSON envelope) and print a small JSON receipt on stdout; `--json`/`--csv` do not refuse when this sink is set.
`webhook:<url>`	POST the output body to the URL (`application/json`)

Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.

Named Profiles

A profile is a saved set of flag values, reused across invocations. Use it when a scheduled or recurring agent reuses the same saved flags while providing different input each run.

game-goat-pp-cli profile save briefing --json
game-goat-pp-cli --profile briefing creator-roles
game-goat-pp-cli profile list --json
game-goat-pp-cli profile show briefing
game-goat-pp-cli profile delete briefing --yes

Explicit flags always win over profile values; profile values win over defaults. agent-context lists all available profiles under available_profiles so introspecting agents discover them at runtime.

Exit Codes

Code	Meaning
0	Success
2	Usage error (wrong arguments)
3	Resource not found
4	Authentication required
5	API error (upstream issue)
7	Rate limited (wait and retry)
10	Config error

Argument Parsing

Parse $ARGUMENTS:

Empty, help, or --help → show game-goat-pp-cli --help output
Starts with install → ends with mcp → MCP installation; otherwise → see Prerequisites above
Anything else → Direct Use (execute as CLI command with --agent)

MCP Server Installation

Install the MCP server:

go install github.com/mvanhorn/printing-press-library/library/media-and-entertainment/game-goat/cmd/game-goat-pp-mcp@latest

claude mcp add game-goat-pp-mcp -- game-goat-pp-mcp

Verify: claude mcp list

Direct Use

Check if installed: which game-goat-pp-cli If not found, offer to install (see Prerequisites at the top of this skill).
Match the user query to the best command from the Unique Capabilities and Command Reference above.

Execute with the --agent flag:

game-goat-pp-cli <command> [subcommand] [args] --agent

If ambiguous, drill into subcommand help: game-goat-pp-cli <command> --help.