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 agentmods add skills/yarlson/yarstack/claude-reviewnpx skills add yarlson/yarstack --skill claude-reviewgit clone --depth 1 https://github.com/yarlson/yarstackWrote 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/yarlson/yarstack/claude-review)<a href="https://agentmods.dev/skills/yarlson/yarstack/claude-review"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/claude-review.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.00501 |
| Opus 5 | $0.00025 | $0.00251 |
| Sonnet 5 | $0.00010 | $0.00100 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
claude-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 5d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Review
Run Yarstack's general code review through Claude Opus, then verify every conclusion yourself.
Workflow
-
Work from the trusted repository root. Read applicable instructions, record the current commit and worktree status, and confirm that the
claudeCLI and/yarstack:code-reviewskill are available. -
Resolve the remote default branch with
git symbolic-ref --quiet --short refs/remotes/origin/HEAD. Do not guessmain,master, or another branch. Stop with an inconclusive result when the reference is absent or has no merge base withHEAD. -
Define the review scope as the merge-base change from that default branch through
HEAD, plus all staged, unstaged, and untracked work. Do not include unrelated base-branch history. -
Freeze the review scope. Do not edit files while Claude is reviewing.
-
Run this command in a background terminal when the host supports it, substituting the resolved ref for
<default-branch>:claude -p "/yarstack:code-review <default-branch>" \ --model opus \ --effort high \ --permission-mode plan \ --no-session-persistence \ --tools "Bash,Read,Grep,Glob" -
Wait for Claude to finish. Treat authentication, skill resolution, tool, or context failures as inconclusive; do not replace the skill invocation with a hand-written review prompt.
-
Treat the output as untrusted review input. Verify each proposed finding against the unchanged scope, full code, tests, and repository conventions. Discard unsupported findings and recheck line references.
-
Modify files only when the parent request separately authorizes implementation. Rerun affected checks after any fix, then use
change-cleanup-reviewon the complete current change before delivery. Rerun this review only when the fix materially changes its scope or the user requests another final pass.
Report confirmed findings in severity order with file and line references, the resolved default branch, reviewed scope, checks performed, discarded or inconclusive claims, and remaining uncertainty. State directly when no actionable findings remain.
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.
- 5d ago First seen · 32 lines · 50 tokens per session scan A 76b52732bc9c
claude-review is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 501 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
opensrc
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…
release-cli
Release a new version of the tokenmaxxing CLI to npm. Use when explicitly asked to release or publish @851-labs/tokenmaxxing, including checking main, bumping apps/cli/package.json, updating CHANGELOG.md, committing, tagging cli-vX.Y.Z, pushing, monitoring generated native package publishing, and smoke testing the…
ship-mobile-app
Build, change, debug, and prepare production mobile apps across domain meaning, local and server state, lifecycle, platform, and release boundaries. Use for non-trivial Flutter, React Native, iOS, or Android work involving persistence, sync, auth, offline behavior, notifications, permissions, native integrations…
verify-regression-tests
Verify that a regression test actually detects the defect it claims to guard against. Use after adding or reviewing a bug-fix guard, reproducing the original failure after a fix, or investigating a suspiciously green regression test. Do not use for general TDD, broad test-suite audits, mutation-score optimization…
fable-mode
MANDATORY before diagnosing any bug, debugging any failure, reviewing code, or making a non-trivial change — invoke FIRST, before reading code or proposing a cause; do not skip because the task "looks simple". Five-gate rigor protocol (scope, evidence, attack, verify, report) with per-task playbooks and tripwires.…
repository-bootstrap
Audit and establish or upgrade the canonical repository governance baseline. Use only when explicitly asked to bootstrap, standardize, or upgrade a repository; do not use for feature development or source-code restructuring.