SuperAPI AI Directory

construct

Coding & development

View repository

Updated 11-06 16:21

About this skill

Construct

Authority

Construct persists no execution state and creates no execution artifact. Blueprint owns every planning decision; Git worktree state owns the implementation delta. Discovery is evidence, not authority: it cannot expand a sealed Blueprint. The Blueprint stays byte-for-byte unchanged. Preserve unrelated dirty work; execution requires a Git worktree. Scripts prove mechanics only; the agent owns attribution, scope truth, and completion.

Command

python <construct>/scripts/cli.py --repo-root <repo> --input blueprint_file=<blueprint.md> --input phase=before --format json verify

Judge criteria first; follow next_command when present, else required_action.

Smooth execution loop

  1. Intake. Read Execution contract once, then run verify before for fresh work, status for resume. For dirty targets, non-Git paths, concurrent, destructive, or recovery work read Safety. Uncertain progress requires caller reconciliation. Read the whole Blueprint before editing.
  2. Implement each ### N. in order. apply writes declared blocks, never by hand: with Red:, apply Frozen, write prose tests, prove its declared red, then apply Exact. Implement the rest, then prove green with the caller-held next unused attempt and follow its forward guidance. Repair only what Blueprint settles; otherwise stop as plan-contradiction.
  3. Verify. Run verify phase after; judge every Expect:. Repair locally only when Blueprint fixes the answer, then reverify from the earliest invalidated Run line. A shown declared Incomplete: outcome ends as verification-incomplete after step 4. Else stop with plan-contradiction evidence. Timeout or mutation failures are unsafe, never reverify.
  4. Reconcile and report. Compare the final diff against the sealed Blueprint once: every instruction realized, no unauthorized change, constraints preserved. When earned, an Earned Conformance Review confirms it. Report instructions, proof and before-implementation verification results, each after-implementation Run with its Expect: and whether its output met it, unrecoverable red gaps, notices, and whether protected paths and HEAD are unchanged.

Exceptions

Stopping ends the Construct run: plan-contradiction, protected-work-conflict, or safety-contradiction, reported with exact evidence. The execution contract's Stopping section owns what happens next.

Final and stop reports end with one optional next step fitting this outcome, after a stop its recovery owner's: a fenced, self-contained prompt naming any repository, issue, PR, or artifact it needs, or say none is needed. Only a "yes" starts it, via any skill it names, but the user runs a charter, diagnose, or ticket step as its /<skill> command.