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 hamr0/liteagents --skill branch-reviewgit clone --depth 1 https://github.com/hamr0/liteagentsWrote 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/hamr0/liteagents/branch-review)<a href="https://agentmods.dev/skills/hamr0/liteagents/branch-review"><img src="https://agentmods.dev/badge/skills/hamr0/liteagents/branch-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/hamr0/liteagents/branch-review"><img src="https://agentmods.dev/badge/skills/hamr0/liteagents/branch-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.06935 |
| Opus 5.5 | $0.00000 | $0.02774 |
| Sonnet 5.5 | $0.00000 | $0.01387 |
| Haiku 4.5 | $0.00000 | $0.00694 |
Grade A, and why
branch-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 23d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- branch-review — 95% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-merge review gate. General review, then a full security audit, then an adversarial verify pass, then a docs sweep. It never edits code: findings are reported and handed back, and fixing is a separate, separately authorized action. The docs sweep is the one stage that writes, and only to docs — it updates the project's docs for what this branch changed and commits exactly that.
Only Critical and High findings block the merge. Everything else is appended to the fix ledger (.amp/remember/fix-ledger.md) — a local, cumulative list, living beside MEMORY.md, usually gitignored, that /refactor (no arguments) works through between features. The report is blockers plus the ledger count. This command never runs /refactor itself — it nudges.
Run this before /release, which refuses to run without a review at the current HEAD SHA.
Guardrails
- Spawn a worker, mid tier stated explicitly (omitted inherits the parent's, not the balanced one; not cheapest/fastest either — judgment degrades there; never a vendor model name), and hand it this file's path — a worker has no skill text of its own. Fall back to running inline if your tool has no subagent mechanism.
- Escalate, never assume. Anything you cannot decide, cannot verify, or that this spec does not cover → stop and report it to the orchestrator (the main session). Never improvise, never widen scope, never fix a side issue you noticed along the way.
- The worker does the work itself — no delegation. The review subagent must not spawn subagents of its own. Everything it reports has to be something it read, ran, or grepped with its own tool calls; a relayed "I executed X" is hearsay. (Same rule
/securitycarries inside stage 2.) - No edits — three exceptions. You have no authorization to change code, even for a finding you are certain about. Report it. The only files you may write are
.amp/remember/fix-ledger.md(append bullets; never rewrite or delete),.amp/remember/last-review.md(overwrite; the review record described at the end of this file), and the doc files Stage 4 touches — edited and then committed by that stage alone, never for code, skills, config, or tests. - Prove it with two checks, because neither sees what the other does.
git status --porcelain, at start and again before you report, proves the tree is clean — no code or config changed, and, when Stage 4 ran (review settled), that its doc edits landed as the last act before you report. It cannot police your own two.amp/writes (.amp/is normally gitignored), so also hash the files there before you start and again before you report:
and show the comparison: onlyfind .amp/remember -maxdepth 1 -type f -exec md5sum {} + | sort -k2fix-ledger.mdandlast-review.mdmay differ. And rungit diff --name-only <reviewed sha>..HEADbefore you report: it must list only the files on the record'sdocs:line — anything else means an edit escaped Stage 4's scope. Both results are shown on theproof:line of the closing block.
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.
- 23d ago Changed · -128 lines 67d650040aa6
- 24d ago Changed · +2 lines f93df18e4a41
- 1mo ago Changed · +5 lines 400a7d122e84
- 1mo ago Changed · +56 lines 031356fd2af2
- 1mo ago Changed · +17 lines 17728a56af31
- 1mo ago Changed · +14 lines 7ae8946963e2
- 1mo ago First seen · 343 lines · 0 tokens per session scan A 2585d5350665
branch-review is a skill published in the GitHub repository hamr0/liteagents (26 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 6,935 tokens. 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 2026-09-05.
Other skills, from other repositories
codebase-modernizer
Audit a stale, inherited, or messy codebase — deps, bugs, security, tests, CI, docs, UI/UX — then emit a phased, testable modernization plan. Read-only: plans upgrades, never applies them. Not for single-PR review, PRD-to-tasks, or UX-only audits.
issue-work-loop
Run Herdr loops for one open GitHub issue (resolve→review→fix) or an existing PR (review→lazy fixer) until CLEAN. Don't use for plain resolution without review, review-only/no-fix requests, backlog automation, or merging.
code-review
Review or improve code — one skill, four modes: bug/security review (default), performance, clean-code audit, slop cleanup. Pass mode:review|perf|clean|cleanup or infer. Don't use for writing features or generating tests (use test-coverage).
ahk-review
Preview a code review against ticket/objective alignment, with deep semantic (name-vs-behavior) analysis. No tasks created, no harness tracking.
the-judge
Evidence-first pull request judge that reviews a PR and posts one consolidated GitHub review with inline comments via the gh CLI. Runs the repo's own deterministic checks first, researches current official docs before any claim about external libraries or APIs, then reviews correctness, security, structural quality…
best-practices
Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities". Do NOT use for accessibility (use web-accessibility), SEO (use seo), performance (use…