Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add i9wa4/dotfiles --skill subagent-reviewgit clone --depth 1 https://github.com/i9wa4/dotfilesWrote 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/i9wa4/dotfiles/subagent-review)<a href="https://agentmods.dev/skills/i9wa4/dotfiles/subagent-review"><img src="https://agentmods.dev/badge/skills/i9wa4/dotfiles/subagent-review/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/i9wa4/dotfiles/subagent-review"><img src="https://agentmods.dev/badge/skills/i9wa4/dotfiles/subagent-review.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 | $0.00049 | $0.00500 |
| Opus 5.5 | $0.00020 | $0.00200 |
| Sonnet 5.5 | $0.00010 | $0.00100 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
subagent-review 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.
What it actually says
Subagent Review
1. Ledger and authority
Guardian freezes target, scope, criteria, baseline, mode, and boundary. The
task owner declares mitigation mode before this freeze.
Guardian owns never-reused IDs (F-001), applies the
materiality and risk rules, and decides
convergence. Packets supply evidence; nits do not gate rework. Record gaps.
2. Review loop
- Run cheapest verification. Guardian MUST request critic for substantive review; deduplicate its set and self-review. Reviewers cannot edit, commit, push, approve, or decide materiality. Follow the packet contract.
- Give each prior ID exactly one round disposition: recurrence, regression, closure, supersession, accepted risk, unchanged, or changed criterion. Record new discoveries separately. Record changed/tightened criteria as old/new/reason/owner; never portray them as previously frozen.
- Review the full change; freeze material IDs, observable closure outcomes,
and named verification in one batch. Separate design suggestions. Attribute
reviewer prescriptions and
prescription-inducedregressions; reassess the prescription and gate regressions by materiality. Re-review that batch. - Repeat fix, verification, and diff review through confirmation.
Count
initial,rework 1 of 2,rework 2 of 2; invalid packets consume no slot. At cap or unavailable proof, reportBLOCKEDwith IDs and gaps. Only the human user through the interface node may extend the rework cap. This cap is separate from the Tier 1 attempt cap.
3. Round report
Use the contract's report: counter, frozen criteria/baseline/mode, criterion changes, accepted-risk authority and owners, reviewer-reachable proof, base-versus-head latency/liveness check, ledger, verdict, and next action.
What ships with it
13 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.
- evals/eval.yaml 520 B
- evals/tasks/negative-trigger-1.yaml 457 B
- evals/tasks/negative-trigger-2.yaml 445 B
- evals/tasks/positive-trigger-1.yaml 411 B
- evals/tasks/positive-trigger-2.yaml 475 B
- evals/tasks/positive-trigger-3.yaml 639 B
- references/review-topology.md 15 KB
- references/reviewer-architecture.md 1.5 KB
- references/reviewer-code.md 1.4 KB
- references/reviewer-data.md 1.5 KB
- references/reviewer-historian.md 3.9 KB
- references/reviewer-qa.md 1.8 KB
- references/reviewer-security.md 1.4 KB
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 Changed 5d8aaa75ed12
- 2mo ago First seen · 45 lines · 49 tokens per session scan A f826695e8bbe
subagent-review is a skill published in the GitHub repository i9wa4/dotfiles (12 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 500 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
drift-check
Pre-PR advisory check for deviations from the project spec. Read-only analysis.
codebase-audit
Analyze a git repo's history to surface high-churn files, ownership risks, bug hotspots, momentum trends, and firefighting patterns. Use this skill whenever the user wants to understand a codebase, assess repo health, or orient themselves before reading code — even if they don't explicitly say "audit". Examples…
pr-style
This skill should be used when creating or editing a GitHub pull request title or description, regardless of tool (gh CLI, GitHub MCP tools, API). Defines PR title format and body format with Why/What/Notes sections.
gh-pr
This skill should be used when creating a GitHub pull request via gh pr create. Covers the gh CLI mechanics; PR title and body conventions come from the pr-style skill.
pi-review
A process for getting an independent review of a code or design change from a separate pi review session. The review uses either the sol or luna model and checks the repository or supplied document.
audit
Repo audits, one mode or all (codebase, docs, process, perf, tests, threat-model, motion, SEO, debt). Triggers "audit the codebase", "full audit", "perf audit", "audit the tests", "threat model", "motion audit", "seo audit", "debt ledger".