Borrowing it
Nothing to install: this file belongs to the-sid-dani/second-brain-os. 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/the-sid-dani/second-brain-os/main/.agents/skills/code-review/SKILL.mdgit clone --depth 1 https://github.com/the-sid-dani/second-brain-osWrote 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/the-sid-dani/second-brain-os/code-review)<a href="https://agentmods.dev/skills/the-sid-dani/second-brain-os/code-review"><img src="https://agentmods.dev/badge/skills/the-sid-dani/second-brain-os/code-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/the-sid-dani/second-brain-os/code-review"><img src="https://agentmods.dev/badge/skills/the-sid-dani/second-brain-os/code-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 | $0.00113 | $0.01672 |
| Opus 5.5 | $0.00045 | $0.00669 |
| Sonnet 5.5 | $0.00023 | $0.00334 |
| Haiku 4.5 | $0.00011 | $0.00167 |
Grade A, and why
code-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 7d 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.
This is a copy
81% identical to code-review — 63 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Two-axis review of the diff between HEAD and a fixed point the user supplies:
- Standards — does the code conform to this repo's documented coding standards?
- Spec — does the code faithfully implement the originating issue / PRD / spec?
Both axes run as parallel sub-agents so they don't pollute each other's context, then this skill aggregates their findings.
Resolve the project and its paths from docs/agents/project-context.md. If the repo belongs to no known project, skip that and take the spec from the user's argument or ask; never offer /new-project for a review. A ticket named by number only ("ticket 03") is the project's tickets/03-*.md.
The review is read-only: report findings, never edit the code. Tell both sub-agents the same.
Process
1. Pin the fixed point
Whatever the user said is the fixed point — a commit SHA, branch name, tag, main, HEAD~5, etc. If they didn't specify one, ask for it.
Capture the diff command once: git diff <fixed-point>...HEAD (three-dot, so the comparison is against the merge-base). Also note the list of commits via git log <fixed-point>..HEAD --oneline.
Before going further, confirm the fixed point resolves (git rev-parse <fixed-point>) and the diff is non-empty. A bad ref or empty diff should fail here — not inside two parallel sub-agents.
2. Identify the spec source
Look for the originating spec, in this order:
- Ticket references in the branch name or commit messages (
ticket-03-…,#123) — read the ticket and its parent spec from the project folder perdocs/agents/project-context.md(tickets/NN-slug.mdandspec.md). - A path the user passed as an argument.
- A PRD/spec file under the repo's
docs/orspecs/, or the project'sspec.md, matching the branch name or feature. - If nothing is found, ask the user where the spec is. If they say there isn't one, the Spec sub-agent will skip and report "no spec available".
3. Identify the standards sources
Anything in the repo that documents how code should be written, such as CODING_STANDARDS.md or CONTRIBUTING.md.
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.
- 7d ago First seen · 93 lines · 113 tokens per session scan A f262f4b6812a
code-review is a skill published in the GitHub repository the-sid-dani/second-brain-os (3 stars, last pushed 7d ago), licensed MIT. It adds 113 tokens to every session and 1,672 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 81% identical to code-review, differing in 63 lines, and is treated as a copy.
Other skills, from other repositories
pr-reply
Answer reviewers on your own pull requests in other people's repos: find threads where the ball is on your side, tell humans from bots, do exactly what was asked and reply with evidence. Use at the start of any GitHub session or on a new-review alert. Triggers: /pr-reply, /prr, answer the reviewers, who is waiting on…
outbound-gate
Gate for any outbound message before it leaves: pull request or issue comment, DM, invite, post, email. Use before sending to check facts, tone, platform rules, registry status and AI-slop, and to block text that fails.
codex-review
Cross-vendor code review: this agent reviews the other agent's diff and the other agent reviews this one's, so the final check always comes from a different model. Verdicts are APPROVE or REQUESTCHANGES with file:line references. Triggers: "/codex-review", "cross-review this diff", "have the other vendor check this".
red-first-review
Review someone else's pull request by measuring which of its own guards its own test suite actually catches, via a small mutation matrix. Use when reviewing a PR, checking whether a regression test is real, or asked 'is this change actually tested?', 'does this test do anything', 'mutation test this'.
advisor-intake
An intake workflow for recommendations submitted by external advisors through pull requests or issues in a private GitHub repository. Pull requests propose code or document changes; issues record tasks or discussion.
secondop
Get a second opinion from an external LLM at three checkpoints: T1 is the plan valid, T2 which path at a fork, T3 finish plus a QA breaker that tries to break the result. One structured move per exchange (PROPOSE, COUNTER, VERIFY, ACCEPT, BLOCK) with memory across turns, and every exchange mirrored into a…