Borrowing it
Nothing to install: this file belongs to pandulapeter/campfire. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pandulapeter/campfire/master/.claude/skills/codebase-review/SKILL.mdgit clone --depth 1 https://github.com/pandulapeter/campfireWrote 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/pandulapeter/campfire/codebase-review)<a href="https://agentmods.dev/skills/pandulapeter/campfire/codebase-review"><img src="https://agentmods.dev/badge/skills/pandulapeter/campfire/codebase-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/pandulapeter/campfire/codebase-review"><img src="https://agentmods.dev/badge/skills/pandulapeter/campfire/codebase-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 | $0.00180 | $0.05155 |
| Opus 5.5 | $0.00072 | $0.02062 |
| Sonnet 5.5 | $0.00036 | $0.01031 |
| Haiku 4.5 | $0.00018 | $0.00515 |
Grade A, and why
codebase-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 2d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase review sweeps
A sweep has two halves. The review finds and verifies issues, fixes the simple ones on the spot, one commit each, and writes a plan for each complex one. The execution lands those plans, in a later turn, and only starts when the user says so — never roll from the review into it.
When to run: at milestones only — after a planned program lands, before a major release, or when the owner asks; never after every batch of commits. Between them, the checks in the loop (the edit hook, the pre-commit hook) keep quality.
0. Before anything
- Read the memory notes of earlier reviews (
MEMORY.mdlists them). Do not re-review an area the last sweep found solid, re-raise a finding that was rejected or disproven, or re-ask a decision the user already took — the notes record all three. - Look at the plans folder (see the last section). If plans from an earlier sweep are still there, ask whether to keep them, fold them in or clear them before writing new ones. Never delete untracked plans on your own.
- Note
git rev-parse --short HEADand the branch; every document names that commit, and it is the start of the range the review's own fixes land in. If the working tree has uncommitted work, say so: fixes stage only their own paths, and a finding in a file with pending changes is planned rather than fixed. - Agree on the angle and the budget if the request leaves them open. The yield comes from a new angle (a platform barely run, bad network, low-end devices, scale, stress/monkey tapping, a store's rules), not from looking harder at the same code. If the user caps tokens or time ("an hour is enough"), size the fan-out to it: fewer reviewers, one live run at most.
- Pick each agent's model for its job, without being asked. Judgement — area reviewers, plan writers, challengers,
lane agents — runs on the most capable model. Matching text against the code — the docs check, a regression read of
docs-only commits, applying already-written doc fixes, mechanical moves — runs on a cheaper one (
sonnet;haikufor plain grep-and-compare). Prefer doing a small mechanical job yourself over spawning anything.
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.
- 2d ago Changed 78550b7dd6f4
- 4d ago First seen · 264 lines · 180 tokens per session scan A ce5a9731c7d9
codebase-review is a skill published in the GitHub repository pandulapeter/campfire (119 stars, last pushed yesterday), licensed MPL-2.0. It adds 180 tokens to every session and 5,155 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-11-02.
codebase-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codebase-reviewpandulapeter/campfire | Skill | 119 | yesterday | MPL-2.0 | A | 180 | Claude Code |
| autoreviewopenclaw/clawhub | Skill | 9.5k | yesterday | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 115 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 48 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 945 | yesterday | MIT | A | 84 | Claude Code |
| explore-unknownsdzhng/skills | Skill | 1.4k | 2d ago | MIT | A | 162 | Claude Code, Codex |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | 4d ago | MIT | A | 70 | Claude Code |