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 juanmhidalgo/claude-plugins --skill branch-reviewgit clone --depth 1 https://github.com/juanmhidalgo/claude-pluginsWrote 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/juanmhidalgo/claude-plugins/branch-review)<a href="https://agentmods.dev/skills/juanmhidalgo/claude-plugins/branch-review"><img src="https://agentmods.dev/badge/skills/juanmhidalgo/claude-plugins/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/juanmhidalgo/claude-plugins/branch-review"><img src="https://agentmods.dev/badge/skills/juanmhidalgo/claude-plugins/branch-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 | $0.00032 | $0.02581 |
| Opus 5 | $0.00016 | $0.01290 |
| Sonnet 5 | $0.00006 | $0.00516 |
| Haiku 4.5 | $0.00003 | $0.00258 |
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 3d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Branch Review
Severity Classification
| Level | Block Merge? | Examples |
|---|---|---|
| CRITICAL | Yes | Security vulnerabilities, data loss risks, breaking changes without migration |
| HIGH | Should fix | Bugs affecting users, performance regressions, missing error handling |
| MEDIUM | Recommend | Code smells, minor perf issues, missing non-critical tests |
| LOW | Optional | Style issues, refactoring opportunities, docs |
Labels (orthogonal to severity)
Two labels change how a finding is read, not how severe it is. Both exist so that findings get surfaced and marked instead of silently dropped — a dropped finding is indistinguishable from a review that never looked.
| Label | Meaning | Effect |
|---|---|---|
nit |
Correct, but below the bar a senior engineer would raise in review | Never blocks. Reported in its own group, collapsed by default. |
pre_existing |
Real, but not introduced by these changes | Never blocks this merge. Reported so it can become a ticket. |
Do not use nit as a hedge on a finding you believe matters — that is what
LOW severity is for. nit means "I am reporting this only for completeness".
Never suppress a pre_existing finding to keep the report clean. The rule
is "do not block on pre-existing issues", not "do not mention them". If the
changes made an existing problem materially worse, it is not pre_existing —
it is a finding against these changes.
Confidence Classification
Severity answers "should this block merge?". Confidence answers "how strong is the evidence?". They are orthogonal — always pair both on every finding.
| Level | Meaning |
|---|---|
| HIGH | Verified by reading the code path end to end. Evidence is direct: cited file:line you opened. Not "reproducible" — you cannot run anything; see Evidence provenance. |
| MEDIUM | Strong inference from code patterns or framework behavior; would benefit from runtime confirmation before fixing. |
| LOW | Speculation or pattern-based concern; may not apply in this specific context. Worth flagging, not over-weighting. |
What ships with it
1 file 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.
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.
- 3d ago Changed · +128 lines 30fcf701322f
- 12d ago First seen · 104 lines · 32 tokens per session scan A 4b3e70c8dd8a
branch-review is a skill published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 2,581 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 2026-08-31.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
oss-maintainer
Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.