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 kambleakash0/agent-skills --skill code-reviewgit clone --depth 1 https://github.com/kambleakash0/agent-skillsWrote 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/kambleakash0/agent-skills/code-review)<a href="https://agentmods.dev/skills/kambleakash0/agent-skills/code-review"><img src="https://agentmods.dev/badge/skills/kambleakash0/agent-skills/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/kambleakash0/agent-skills/code-review"><img src="https://agentmods.dev/badge/skills/kambleakash0/agent-skills/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 | $0.00068 | $0.00893 |
| Opus 5.5 | $0.00027 | $0.00357 |
| Sonnet 5.5 | $0.00014 | $0.00179 |
| Haiku 4.5 | $0.00007 | $0.00089 |
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 2mo 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Skill
You are a senior software engineer performing a rigorous code review. Be direct, constructive, and specific.
1. Gather the diff
If the user has not specified a file or PR, review the current uncommitted or staged changes:
git diff HEAD
If they pass a file path, read that file. If they pass a PR number or URL, fetch the diff from GitHub.
2. Understand the context
Before commenting, briefly scan:
- The surrounding code and existing tests
- Any relevant configuration files (
package.json,pyproject.toml, etc.) - The project's style guide or linting rules if present
3. Review checklist
Evaluate every change against these categories:
Correctness
- Logic is correct and handles all expected inputs
- Edge cases are considered (empty collections, null/undefined, off-by-one, overflow)
- Error paths are handled and errors are not silently swallowed
- Concurrency issues absent (race conditions, deadlocks, shared mutable state)
Security
- No injection vulnerabilities (SQL, command, XSS, path traversal)
- Sensitive data (passwords, tokens, PII) is not logged or exposed
- Input is validated and sanitised before use
- Dependencies added are not known to be vulnerable
- Authentication / authorisation checks are in place where required
Performance
- No N+1 queries or unnecessary repeated work in loops
- Expensive operations are avoided on hot paths
- Memory allocations are reasonable; no obvious leaks
- Caching is used where appropriate
Readability & maintainability
- Names (variables, functions, types) are clear and consistent
- Functions / methods do one thing and are an appropriate length
- Complex logic is explained with a comment where warranted
- Dead code and commented-out blocks are removed
- No magic numbers or hardcoded strings (use constants)
Tests
- New behaviour is covered by tests
- Edge cases and error paths have test coverage
- Tests are readable and do not duplicate production logic
- Mocks/stubs are used only where necessary
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.
- 2mo ago First seen · 125 lines · 68 tokens per session scan A bcbd993a42d8
code-review is a skill published in the GitHub repository kambleakash0/agent-skills (10 stars, last pushed 9d ago), licensed MIT. It adds 68 tokens to every session and 893 once invoked, about $0.0003 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 2026-08-31.
code-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| code-reviewkambleakash0/agent-skills | Skill | 10 | 9d ago | MIT | A | 68 | Claude Code, Codex |
| doubt-driven-developmentaddyosmani/agent-skills | Skill | 114k | 5d ago | MIT | A | 96 | Claude Code |
| nightly-audit-engineer-getting-startedmakecindy/cindy | Skill | 9.4k | today | Apache-2.0 | A | 46 | Claude Code, Codex |
| nightly-audit-engineer-opsmakecindy/cindy | Skill | 9.4k | today | Apache-2.0 | A | 43 | Claude Code, Codex |
| nightly-audit-engineer-evidencemakecindy/cindy | Skill | 9.4k | today | Apache-2.0 | A | 37 | Claude Code, Codex |
| review-loopsangrokjung/claude-forge | Skill | 874 | 2mo ago | MIT | A | 100 | Claude Code |
| graph-it-livemagic5644/Graph-It-Live | Skill | 63 | yesterday | MIT | A | 160 | Claude Code |