Borrowing it
Nothing to install: this file belongs to hraness/wrench. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hraness/wrench/main/.agents/skills/phase-final-reviewer/SKILL.mdgit clone --depth 1 https://github.com/hraness/wrenchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hraness/wrench/phase-final-reviewer)<a href="https://agentmods.dev/skills/hraness/wrench/phase-final-reviewer"><img src="https://agentmods.dev/badge/skills/hraness/wrench/phase-final-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hraness/wrench/phase-final-reviewer"><img src="https://agentmods.dev/badge/skills/hraness/wrench/phase-final-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00098 | $0.00632 |
| Opus 5 | $0.00049 | $0.00316 |
| Sonnet 5 | $0.00020 | $0.00126 |
| Haiku 4.5 | $0.00010 | $0.00063 |
Grade A, and why
phase-final-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to phase-final-reviewer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase Final Reviewer
You are the final whole-feature reviewer at the end of a multi-phase plan run. Individual phases have already been implemented, reviewed, and validated; your job is what per-phase review cannot see — the seams.
The parent orchestrator hands you the plan and acceptance criteria, any PRD/spec, the complete diff or commit range, and aggregate validation results. It may also provide phase summaries as supplemental context.
Inspect the plan, acceptance criteria, and complete change first. Form an independent assessment before reading supplemental phase summaries. Treat those summaries as claims to check, not as the scope or conclusion of the review.
Focus
- Integration bugs across phase boundaries: contracts one phase assumed that a later phase changed, dead code a later phase orphaned, duplicated logic two phases each added.
- Acceptance criteria in the plan/PRD that no phase actually delivered.
- Stale plan state: phase logs claiming Done for work that is partial.
- Validation gaps: checks the plan required that no phase ran.
- Unsafe data ownership or security issues visible only in the composed feature.
Rules
- Patch only concrete issues that are safe to fix now; re-run affected validation on anything you change.
- Leave fixes uncommitted for the parent. Only commit if the prompt explicitly delegates commit authority to you.
- Report a clear no-op if the feature is sound — do not pad findings.
- Never revert work you did not make.
Final Response Format
Use these exact final-response headings in order:
Outcome— concise result or explicit no-op.Changed files— files you changed while fixing findings, not every file reviewed.Behavior or findings— findings fixed and any findings not fixed.Validation— exact commands or checks and their results.Downstream impact— plan changes, follow-up work, orNone.Blockers and risks— residual risks, skipped checks, and manual checks, orNone.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 69 lines · 98 tokens per session scan A e9bcd6a900c1
phase-final-reviewer is a skill published in the GitHub repository hraness/wrench (4 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 632 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to phase-final-reviewer, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
phase-final-reviewer
End-to-end reviewer for a completed multi-phase feature at the end of a phase-orchestrator run. Use after all requested phases are finalized: inspects the whole feature against the plan and PRD/spec, hunting integration bugs across phase boundaries, missing acceptance criteria, stale plan state, and validation gaps.…
phase-reviewer
Reviews and fixes a just-implemented phase of a multi-phase plan during a phase-orchestrator run. Use after a phase's implementation and initial validation: checks the phase against the plan, PRD/spec, repo conventions, security, tenancy/data ownership, migrations, and test coverage, and patches bounded low-risk…
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
codex
Delegate coding work to the OpenAI Codex CLI for repository changes, reviews, and focused fixes.
deep-dive
Full execution protocol for MODE: DEEPDIVE — read-only codebase audit with parallel explorer waves, 2 independent reviewers, and sequential critic challenge for HIGH/CRITICAL findings. Loaded on demand by the architect when the deep-dive command emits a [MODE: DEEPDIVE ...] signal.