evidence

Evidence

A claim is worth exactly what was done to check it. This skill fixes the vocabulary for how much was done, and the handful of checks that turn a plausible sentence into a verified one. The other skills cite these rules by id where they make a claim; the ids are stable and live in rules/registry.json. The decider named across this set is the role that approves and gives go-aheads: a role, not a person.

When to use

Situation	Rule
A sentence states a fact about code, data, a system or a person's work	EVID-1
The fact is about running behaviour	EVID-2
The fact came from an agent, a retrieval system or a review bot	EVID-3
A summary, digest or excerpt is on offer instead of the source	EVID-4
A number is about to lead a message or a document	EVID-5
One defect was just found	EVID-6
A finding is about to be filed against someone else's code	EVID-7
A file is about to be asserted or edited	EVID-8
Custom code is about to be written	EVID-9
A research task read a source that taught something	EVID-10

The tags

Tag	Meaning	What earns it
Verified	the source was opened in this session	the file, log, record or page, read at the cited location
Measured	a number with the query that produced it	the command or query, repeatable
Inferred	reasoning from evidence, not the evidence itself	the premises named
Planned	intended, not done	a step in a plan

Never upgrade a level. Merged is not deployed. Deployed is not verified in data. "Live", "100%", "PASS", "confirmed", "resolved" and "on track" need matching evidence; "green" is never a status. Give the sha, the date and the lane, or the gate.

The rules

Id	Rule	What it means in practice
EVID-1	Tag every claim	Each factual clause carries a tag; a reader treats an untagged clause as Inferred, which is rarely what was meant. Calibration is labelled honestly: "unverified", never blank.
EVID-2	Verify at the production sha	file:line at the sha found from the live artifact or the deployment record, never a branch head or the latest tag. Behaviour comes from production data; dates from the deployment record. Code alone is a hypothesis; an absence claim needs data.
EVID-3	Agent output is a lead	A sub-agent's quote, a retrieval hit or a bot's finding points at a line; the author opens that line before it is used. A quote is verbatim only after the author compared it.
EVID-4	Read sources in full	A summary is a pointer to the source. Slice a large source rather than skip it. Say which sources were read in full and which were not.
EVID-5	Compute a headline number twice	Second method, different path. Never divide counts from two systems with different identity models without the join. A number that moves between identical runs is a harness artefact (TEST-6).
EVID-6	Sweep after one defect	Name the pattern, list every surface, report each as confirmed, not affected, or not checked. "Not checked" is a valid, honest row.
EVID-7	Refute before filing	The second pass argues the other side. If the finding survives, file it with both passes shown.
EVID-8	Re-read before asserting	Especially after checkout, stash or rebase, and before updating a change request whose state may have moved.
EVID-9	Survey before building	Tool, data source, maintenance, fit: record it, name the pick. Custom code covers only the gap. A vendor's or partner's definition of a mechanism wins over a new mode.
EVID-10	Record what a source taught	A dated document in the topic folder: question, sources (full or partial), method, findings with evidence, open questions, exact commands. Never overwrite the earlier one.

Weighting evidence

Weight evidence by what it cost to produce: shipped code, then a written design, then a documented observation, then an opinion. A claim resting on the cheapest kind is Inferred until the costlier kind is opened.

How to apply in a session

1. Before answering on a topic, open what is already established (the topic's memory or dated documents), lead with that, then add what is new.
2. While working, tag as you write. An untagged clause reads as Inferred, which is rarely what was meant.
3. Before showing a deliverable, run the self-review in review-change (REVIEW-7).
4. After a research task, write the dated document (EVID-10) before moving on.

What a tagged paragraph looks like

The retry loop re-sends non-idempotent requests (Verified: src/client/send.py:142 at the production sha 3f9c2ab, from the deployment record of 2026-10-08). It produced 17 duplicate orders last week (Measured: SELECT count(*) … WHERE created_at > '2026-10-01' on the production replica, re-computed from the payment provider's export: 17). The cause is the timeout after the server accepted the write (Inferred from the request logs; no direct evidence of the accept). A fix with an idempotency key is in review (Planned).

Four clauses, four tags, one number computed twice (EVID-5), the inference marked as an inference rather than upgraded to a finding (EVID-1).

Companion skills

Need	Skill
The adversarial read before showing work	review-change
The words that need evidence, and the form of a verdict-first message	plain-voice
Where decision records and glossaries live	decision-records
Plans with assumptions tied to tests	plan-project