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 emaballarin/ccplugins --skill review-gategit clone --depth 1 https://github.com/emaballarin/ccpluginsWrote 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/emaballarin/ccplugins/review-gate)<a href="https://agentmods.dev/skills/emaballarin/ccplugins/review-gate"><img src="https://agentmods.dev/badge/skills/emaballarin/ccplugins/review-gate/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/emaballarin/ccplugins/review-gate"><img src="https://agentmods.dev/badge/skills/emaballarin/ccplugins/review-gate.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 | $0.00137 | $0.01253 |
| Opus 5.5 | $0.00055 | $0.00501 |
| Sonnet 5.5 | $0.00027 | $0.00251 |
| Haiku 4.5 | $0.00014 | $0.00125 |
Grade A, and why
review-gate 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 12d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ws:review-gate — a second reader before the change is acted on
The context that built a change shares its author's blind spots: it reads the
diff through the reasoning that produced it. The gate puts the change in front
of a reader with fresh context, who sees what was written and what was
asked for, and nothing in between. Scale it with blast radius: a one-flag tweak
skips it; an audit script, a release, or a change feeding an experiment never
does — except the per-iteration commits of an autonomous loop the operator
started (/ar:resume), which the loop's own measurement gates.
1. Scope
Take the first that applies, and state it in one line:
- What the operator named — a commit range, a branch, a set of files.
- In a git repository: before a commit, everything against
HEAD(git diff HEADplus untracked files fromgit ls-files --others --exclude-standard, as wholly new hunks); before a release or merge, everything since the merge base with the default branch. In a repository with no commits yet, everything against the empty tree —git diff $(git hash-object -t tree /dev/null)— plus untracked files. - Outside git: the files the task touched, whole. Say so — the reviewer then judges content, not a delta.
An empty scope is not a pass. Stop and say there is nothing to review.
2. Write the intent
In at most five lines, from the request as given: what the change must do, what it must leave alone, and the observable condition that means it is done. Use the request's terms. The intent describes the goal, never the route — no account of how the change was built or why a choice was made. It is the reviewer's only statement of what was asked for.
3. Dispatch one fresh reviewer
Spawn one fresh sub-agent — a new agent that starts with an empty context,
never a fork or any mode that carries this conversation over (in Claude Code:
general-purpose, never fork) — and give it exactly four things: the scope, the intent, the
checklist below, and the output format. Nothing else from the session — no
plan, no rationale, no earlier findings. Tell it to read whatever surrounding
code it needs to judge a hunk, and that it reports and edits nothing.
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.
- 12d ago Changed · +1 lines · +22 tokens per session 0431ef2774ef
- 13d ago First seen · 101 lines · 115 tokens per session scan A 44ce8beec442
review-gate is a skill published in the GitHub repository emaballarin/ccplugins (4 stars, last pushed 6d ago), licensed MIT. It adds 137 tokens to every session and 1,253 once invoked, about $0.0005 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 2026-10-03.
Other skills, from other repositories
pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
han-release
Cut a Han release: update CHANGELOG.md with the changes since the last release, bump and tag every plugin that changed as {plugin-name}--v{version} so a version-constrained dependency can resolve, and publish a GitHub release crediting every merged pull request and closed issue to the people behind it. Use when…
smart-git-commit
Use this skill for ANY git operation — commits, pushes, PRs, releases, or version tagging. Triggers on: "commit", "push", "save my changes", "create a PR", "open a pull request", "ship this", "make a release", "tag this version", "checkpoint my work", or any request to record or publish code changes. Produces…
phx-watch-pr
Watch an Elixir/Phoenix PR with an Amp Orb keep-alive lease until required non-deployment CI is green and review threads are resolved.
git-for-research-code
When the user wants to version-control optimization research code - small commits per experiment change, tags for paper result snapshots, .gitignore for solver logs, linking result tables to commit hashes, and branch strategy for risky refactors. Also use when the user mentions "git workflow," "version control…