agentleFS
aaronreneaaronrene/knowtation/.cursor/skills/independent-second-reviewer/SKILL.md

independent-second-reviewer

Skill1 starsChanged yesterdayMITView on GitHub

Independent second reviewer — second chat / separate verifier records an independent_second_review ledger pass before Auto ROADMAP DONE when ISR is warn or require. Kit records/gates only; does not run another model.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    When honesty.require_verification_evidence is warn or require, also append / confirm Mode B verification_evidence (V8) before claiming DONE.

    line 45
  2. Very specific:

    When ISR config is off, this skill is advisory.

    line 50
  3. Very specific:

    Never merge to main. Never call a model via the kit CLI for this gate (ok review --freeze remains the K5 spec reviewer, not the ISR …

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Independent second reviewer

Invoke: /independent-second-reviewer.

The kit records and gates the second verdict. It does not run another model. Open a new chat or a separate verifier runtime; then use the CLI below.

Portable paste (any host): docs/INDEPENDENT-SECOND-REVIEWER.md.

Process (frozen)

  1. Confirm this session is not the builder session. If it is, stop and tell the operator to open a second chat. Do not append a pass. Do not write ROADMAP DONE.
  2. Re-run /build-verification-review V1–V8 only against the frozen spec + diff (implementation honesty). V9 is not part of this step — it is the DONE-unlock check and cannot be satisfied before the append in step 3.
  3. On V1–V8 pass, append independent_second_review with isr_verdict: pass, this session as actor_session_id, and the builder nonce as producer_session_id:

    ok ledger append --kind independent_second_review --stdin <<'EOF'
    {
      "kind": "independent_second_review",
      "actor_role": "verifier",
      "actor_session_id": "<THIS_CHAT_SESSION_ID>",
      "phase_id": "<PHASE_ID>",
      "frozen_spec": "<FROZEN_SPEC_PATH>",
      "round": 1,
      "isr_verdict": "pass",
      "producer_session_id": "<BUILDER_PRODUCER_SESSION_NONCE>"
    }
    EOF
  4. When honesty.require_verification_evidence is warn or require, also append / confirm Mode B verification_evidence (V8) before claiming DONE. ISR does not replace Mode B.
  5. ROADMAP DONE is allowed only after step 3 (and step 4 when it applies). That is when V9 holds if ISR is warn or require.
  6. When ISR config is off, this skill is advisory; Mode D / status do not fail.
  7. findings / blocked on V1–V8: do not append isr_verdict: pass. A findings ISR append is allowed but not required.
  8. Never merge to main. Never call a model via the kit CLI for this gate (ok review --freeze remains the K5 spec reviewer, not the ISR dispatcher).

Check

ok honesty-status --independent-second-review PHASE_ID \
  [--producer-session BUILDER_NONCE] [--frozen-spec PATH] [--json]

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.