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 marchatton/agent-skills --skill wf-reviewgit clone --depth 1 https://github.com/marchatton/agent-skillsWrote 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/marchatton/agent-skills/wf-review)<a href="https://agentmods.dev/skills/marchatton/agent-skills/wf-review"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/wf-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/marchatton/agent-skills/wf-review"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/wf-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 | $0.00046 | $0.01295 |
| Opus 5 | $0.00023 | $0.00647 |
| Sonnet 5 | $0.00009 | $0.00259 |
| Haiku 4.5 | $0.00005 | $0.00129 |
Grade A, and why
wf-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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wf-review
Purpose
Review changes at the right depth, then produce a clear GO/NO-GO with evidence.
Default mode: light-plus.
Always run basic verification (verify skill). Treat review as provisional if verification cannot be run.
Note on plan.md
plan.md may not exist (it’s optional).
Review should still be completed against:
prd.jsonacceptance criteria (preferred), orprd.md- the actual diff
- verification results
Args (free text)
Parse mode + target from user text.
Mode tokens (first match wins):
lightlight-plusheavy
Accept either:
wf-review light PR#123wf-review mode: heavy target: <url>wf-review <target>(mode missing)
Target examples:
- PR number/URL
- branch name
- file path (doc review)
- dossier folder path
- empty = current branch
If mode missing: default light-plus. If target missing: default current branch (but ask if ambiguous).
Outputs
All modes:
- Review summary + severity (P1/P2/P3)
- Verification result (verify skill) + GO/NO-GO
- Explicit check against PRD acceptance criteria
- Optional handoff notes (recommended)
Heavy only:
- Todo files for findings (file-todos skill)
Mode behaviours
light
Minimum: run verify skill and then native /review only (no extra passes).
Use when:
- small diffs
- low risk
- you mostly want a sanity check
light-plus (default)
Run:
- verify skill
- native
/review - repo prompt review:
/rp-review
Use when:
- most PRs
- you want repo-specific conventions checked too
heavy
Do light-plus, then:
- deep scenario passes (security, data integrity, ops)
- synthesize + de-dupe
- create todos for all findings (file-todos)
- optional
test-browserif UI/user flow changed - final GO/NO-GO
Use when:
- auth/payments/privacy/external APIs/migrations
- big refactors / large surface area
- repeated CI failures / flaky behaviour
- user explicitly asks for “thorough”
Steps (all modes)
- Determine mode + target
- mode default light-plus
- target default current branch (unless user says otherwise)
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.
- 7d ago First seen · 179 lines · 46 tokens per session scan A b39177fdd0aa
wf-review is a skill published in the GitHub repository marchatton/agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 1,295 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…