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 cboone/agent-harness-plugins --skill review-branchgit clone --depth 1 https://github.com/cboone/agent-harness-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/cboone/agent-harness-plugins/review-branch)<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/review-branch"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/review-branch.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 | $0.00105 | $0.03616 |
| Opus 5 | $0.00053 | $0.01808 |
| Sonnet 5 | $0.00021 | $0.00723 |
| Haiku 4.5 | $0.00011 | $0.00362 |
Grade A, and why
review-branch 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 8d 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 — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Branch
Review and evaluate all work done on the current branch: summarize changes, assess plan compliance, and evaluate code quality on its own merits.
Options
The user may provide these options inline:
- --plan
<path>: Path to a plan document to compare progress against - --since
<ref>: Use a specific tag, branch, or commit as the base reference instead of the default branch - --brief: Output only a high-level summary without the detailed breakdown
- --no-save: Skip saving the review to
docs/reviews/(default: save after outputting)
Workflow
1. Determine the Base Reference
Identify the base to diff against:
- If
--since <ref>was specified, use that ref as the base. Verify it exists:
git rev-parse --verify <ref>
- Otherwise, detect the repository's default branch:
gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name'
If gh is not available or the command fails, fall back to a purely local query of the remote HEAD ref:
git rev-parse --abbrev-ref origin/HEAD | sed 's@^origin/@@'
- Find the merge base between the base reference and HEAD:
git merge-base < base-ref > HEAD
Use this merge base as the actual comparison point for all subsequent commands. This ensures the diff only includes changes made on this branch, not changes made on the base branch since diverging.
If HEAD equals the merge base (no commits on this branch), report that there are no changes to review and stop.
2. Gather Changes
Run these commands in parallel:
# Commit history on this branch
git log --oneline < merge-base > ..HEAD
# File-level summary (insertions, deletions, renames)
git diff --stat < merge-base > ..HEAD
# Full diff for detailed analysis
git diff < merge-base > ..HEAD
# Current branch name
git branch --show-current
# Current HEAD commit (for "Reviewed through" metadata)
git rev-parse --short HEAD
Also read the commit messages in detail to understand the intent behind each change:
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.
- 8d ago First seen · 366 lines · 105 tokens per session scan A 0e4cc82ac31f
review-branch is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 3,616 once invoked, about $0.0005 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
05-review
Review a diff read-only on three axes, code, behavior versus the plan, and relevancy, into one verdict report. Use before shipping a change. Not for fixing findings or auditing a codebase.
gh-address-comments
Implements the fixes a PR review asked for — maps each thread to the code it touches, edits that code, and drafts a reply per thread for approval before anything is posted. Starts from feedback that is already understood; producing the read-only digest is pr-comments.
github-address-comments
Implements the fixes a PR review asked for — maps each thread to the code it touches, edits that code, and drafts a reply per thread for approval before anything is posted. Starts from feedback that is already understood; producing the read-only digest is pr-comments.
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…