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 lexfrei/ccc --skill branch-reviewgit clone --depth 1 https://github.com/lexfrei/cccWrote 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/lexfrei/ccc/branch-review)<a href="https://agentmods.dev/skills/lexfrei/ccc/branch-review"><img src="https://agentmods.dev/badge/skills/lexfrei/ccc/branch-review.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 140 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- low Excessive Agency · line 125 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00179 | $0.05458 |
| Opus 5 | $0.00089 | $0.02729 |
| Sonnet 5 | $0.00036 | $0.01092 |
| Haiku 4.5 | $0.00018 | $0.00546 |
Grade A, and why
branch-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Important: If the current directory is not a git repository, ask the user where the target repository is located before proceeding.
CRITICAL: Do not switch branches in the user's repo. If the active branch is the one to review, analyze it in place using git diff, git log, git show. If the active branch is NOT the target (for example when this skill is cascaded from /pr-review and the active branch is master/main while the target is a feature branch), create a temporary git worktree pinned to the target branch and run all analysis there:
WORKTREE_DIR=$(mktemp -d -t branch-review-XXXX)
trap 'git worktree remove --force "$WORKTREE_DIR" 2>/dev/null' EXIT INT TERM
git worktree add "$WORKTREE_DIR" <target-branch>
# All git operations use: git -C "$WORKTREE_DIR" diff/log/show ...
# All file reads are relative to "$WORKTREE_DIR"
# The trap above removes the worktree on every exit path (success, error, interrupt)
Rationale: switching branches in the user's main repo would clobber their working state. A worktree gives an isolated checkout of the target branch without disturbing the active one. The "stay on the active branch" intent is preserved — the active branch is never touched.
Arguments
Parse $ARGUMENTS for:
- Path to repository directory (positional, an existing directory path — e.g.
~/git/github.com/org/repoor../my-worktree). If provided, ALL git and file operations must run inside this directory --targetthe branch this PR is merging INTO (e.g.next,develop,main). This is the most important parameter for determining the correct diff scope--nitpickflag for pedantic mode--typeproject type (e.g.go,node,python,rust,kernel) — skips auto-detection.kernelmeans a patch series bound for a kernel mailing list: the unit of review is each commit over the base, and the "Kernel patch series" criteria below apply--excludeadditional exclude patterns, comma-separated (e.g.docs/,*.gen.go)--ticketticket reference — URL (GitHub issue, Jira, Linear, Notion, etc.) or ID (e.g.#123,PROJ-456). When provided, the review includes a Ticket Compliance section that validates whether the changes fulfil the ticket requirements--round1-headthe head SHA the FIRST review round of this gate ran on — copy it from that round's output header (theReviewed <branch> at <sha>line). Used only to compute finding-origin labels (feature vs churn, see "Finding origin and the churn mark"); it never affects severity or the verdict, so it is an auditable record of a past run, not a scope declaration. Omit on the first round
Examples:
/review-branch→ auto-detect everything in current directory/review-branch ~/git/github.com/org/repo→ review in that directory/review-branch --target next→ review changes going intonext/review-branch --nitpick→ pedantic mode/review-branch --type go --exclude "api/generated/"→ Go project, extra excludes/review-branch --ticket https://github.com/org/repo/issues/42→ validate against GitHub issue/review-branch --ticket PROJ-456→ validate against ticket ID (fetched via appropriate tool)/review-branch ~/worktrees/feature --target develop --nitpick --type node→ all combined/review-branch --target main --ticket #123 --nitpick→ target main, validate against ticket, pedantic mode/review-branch --target main --round1-head 1a2b3c4→ re-review round with churn diagnostics
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 First seen · 278 lines · 179 tokens per session scan A faf24447061d
branch-review is a skill published in the GitHub repository lexfrei/ccc (10 stars, last pushed 5d ago), licensed BSD-3-Clause. It adds 179 tokens to every session and 5,458 once invoked, about $0.0009 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 2026-09-04.
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…
write-pr
Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.