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.
git clone --depth 1 https://github.com/damusix/atomic-claudeWrote 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/commands/damusix/atomic-claude/review-branch)<a href="https://agentmods.dev/commands/damusix/atomic-claude/review-branch"><img src="https://agentmods.dev/badge/commands/damusix/atomic-claude/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 | $0.00035 | $0.00850 |
| Opus 5 | $0.00017 | $0.00425 |
| Sonnet 5 | $0.00007 | $0.00170 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
review-branch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thin wrapper. Runs atomic-reviewer once on <base>..HEAD, returns its standard ## Spec compliance + ## Code quality + signals block + VERDICT: output.
Pre-flight
git rev-parse --is-inside-work-tree
If not in a git repo, stop:
not a git repo. /review-branch needs a versioned project.
Determine base:
gh repo view --json defaultBranchRef -q .defaultBranchRef.name 2>/dev/null \
|| git config init.defaultBranch \
|| echo main
Verify current branch is not the base:
git branch --show-current
If on base: refused: already on <base>. /review-branch reviews a feature branch against its base.
Verify there are commits to review:
git rev-list --count <base>..HEAD
If 0: refused: no commits on this branch ahead of <base>. nothing to review.
Dispatch
Capture the SHAs:
BASE_SHA=$(git merge-base <base> HEAD)
HEAD_SHA=$(git rev-parse HEAD)
FEATURE=$(git branch --show-current)
Invoke the Agent tool with:
-
subagent_type: "atomic-reviewer" -
description: "Review <feature> against <base>" -
prompt:Review the diff <base>..HEAD on the current branch. No spec is provided — this is a pre-PR / pre-merge branch review, not a spec-compliance check. Branch: <feature> Base: <base> Base SHA: <BASE_SHA> HEAD SHA: <HEAD_SHA> Repo: <pwd> Skip the spec-compliance pass — emit `## Spec compliance\n\n(no spec — branch review only)`. Run the code-quality pass thoroughly. Verify TDD signals as usual: - typecheck (project-detected command from docs/wiki/index.md if present) - tests - build - lint Emit the standard output format ending with VERDICT: PASS or VERDICT: CHANGES_REQUESTED.
Report
Pass the reviewer's output through to the user verbatim. Do not summarize, do not add commentary — the reviewer's findings are the deliverable.
Append one line at the end:
suggested next step (on PASS):
/commit pr → open PR for review
/commit merge → merge into <base>
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 · 130 lines · 35 tokens per session scan A 6e16a1179484
review-branch is a command published in the GitHub repository damusix/atomic-claude (85 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 850 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 2026-08-30.
Other commands, from other repositories
dream
Overnight autoresearch + maintainer sweep that surfaces a MORNING REPORT — suggested changes, issues raised with fixes, and kept improvements. Shadow-first; never auto-pushes. Runs on-demand or scheduled for off-hours.
audit-mirage-analyze
Phases 2-3 and 7 of auditing-green-mirage: systematic line-by-line audit, the Green Mirage Patterns, named assertion shapes, and the fix-verification Test Adversary prompt.
address-pr-feedback
Systematically address PR review comments. Fetches all threads, categorizes by status (acknowledged, silently fixed, unaddressed), and guides user through posting replies and implementing fixes with explicit approval.
advanced-code-review-context
Advanced Code Review Phase 2: Context Analysis - load previous reviews, PR history, declined items.
advanced-code-review-plan
Advanced Code Review Phase 1: Strategic Planning - scope analysis, risk categorization, priority ordering.
advanced-code-review-review
Advanced Code Review Phase 3: Deep Review - multi-pass code analysis, finding generation with severity classification.