loop-spec

Loop spec

Execute the per-wave Pass-1 loop:

implement TASK → check/test → fix → record local proof → repeat
→ write Wave-Execution + Forge commit_workspace readiness
→ stop at wave-acceptance (human prove + patch tip)

Closeout (/learning-extract → /ground-spec) is a separate Pass-2 after human wave-acceptance — not this skill's job.

Content skills write locally and emit Forge readiness; they do not commit, push, branch, open PRs, label, create issues, or merge.

Conventions: prayog-skills/references/id-conventions.md, prayog-skills/references/artifact-write-contract.md.

Canonical artifact after the wave is green: {reports_dir}/Wave-Execution-{INIT}-W{N}.md.

NON-NEGOTIABLE

1. Implement against the product spec only — do not implement scope from the next wave.
2. Prerequisites — run only after /pre-implement produced a checklist with gate verdict PASS on the current wave. Do not run on an open Draft spec PR branch (chore/*-spec-*). The implementation plan must exist on develop (spec package merged with spec-lgtm on merge head). Wave head is bound by Forge/human context. Canonical §9 WorkManifest (prayog/v1) must already have passed contract validation at pre-implement.
3. Consume WorkManifest tasks — execute TASK-* for this wave in dependency order (depends_on DAG within the wave). Remain within each TASK's declared files[] path/action scope. Do not mutate the approved WorkManifest intent (no rewriting exit criteria, deps, or live contract in §9). Persist actual command/evidence results only in Wave-Execution-{INIT}-W{N}.md and the stage handoff.
4. After each TASK, run {check_command} and {test_command} from the harness profile (or tests_readme) — check/unit layers only. Both must pass before recording the TASK complete. Implement co-shipped live FILE TASKs (scripts under live_verify_dir and fixture packs under fixtures_dir) when the plan/manifest includes them — deliver stimulus + probes per live-fixture-contract.md; do not execute live verify, verify_all, or {verify_command} as this skill's success bar, and never claim human smoke/sandbox success or opaque look-at pass.
5. Fix failures before moving to the next TASK — do not accumulate failures.
6. When all TASKs are green: write Wave-Execution-{INIT}-W{N}.md, emit completed TASK-* IDs/evidence (observed commands + results), fill commit_workspace readiness and complete handoff.forge for next wave-pr-action (open_draft_pr requires). Do not run /ground-spec or /learning-extract in this hop. Do not self-approve the wave. Handoff MUST list human prove: {verify_command}, covered CAP-* / J-*, fixture paths, and any human_observations look-ats.
7. Do not skip check/test steps to save time.
8. Bind execution — each iteration names TASK-W{n}-{nn}, the wave board issue URL/number, and implements: [REQ-…] from the WorkManifest (board body is projection only).
9. Structured failures — on check/test failure, record under handoff blockers the TASK-* id plus command and short why; prepare optional issue-comment Forge readiness when tooling is authorized elsewhere. Do not advance while any TASK blocker remains.
10. Never commit or push inside this skill — not per TASK and not at wave end. ForgeClient or /commit-workspace publishes the workspace tree to the bound wave head after this hop when the pin requires it.