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 agentmods add skills/hejiguang/codescan/codescan-reviewnpx skills add HeJiguang/codescan --skill codescan-reviewgit clone --depth 1 https://github.com/HeJiguang/codescanWrote 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/hejiguang/codescan/codescan-review)<a href="https://agentmods.dev/skills/hejiguang/codescan/codescan-review"><img src="https://agentmods.dev/badge/skills/hejiguang/codescan/codescan-review.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 | $0.00055 | $0.00583 |
| Opus 5 | $0.00028 | $0.00292 |
| Sonnet 5 | $0.00011 | $0.00117 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
codescan-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 6d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeScan Review
Overview
Use CodeScan as a focused security reviewer. Prefer MCP tools when they are available. Fall back to the CLI only when MCP is unavailable.
Prioritize exploitable findings over style issues or generic code smell commentary.
When To Use
- The user asks for a security review or vulnerability scan
- The user wants a pre-merge or branch-diff review
- The code under review handles auth, secrets, input validation, file access, command execution, SQL, HTML rendering, network callbacks, or crypto
- The user wants CodeScan specifically, not just a generic security opinion
Do not use this skill for general refactoring, style cleanup, or performance review unless the user explicitly widens scope.
Tool Selection
- Use
scan_filefor a focused review of one file - Use
scan_directoryfor repository or module sweeps - Use
scan_git_difffor active-branch or pre-merge review - Use
scan_github_repowhen the target repo is only available as a Git URL
Prefer the smallest scope that answers the user's request.
Workflow
- Pick the narrowest scan that matches the request.
- Run CodeScan through MCP first.
- Read the structured findings and separate strong signals from weaker suspicions.
- Manually inspect any
criticalorhighfinding before presenting it as real. - Respond with findings first:
- severity
- file path and line
- why it is risky
- concrete remediation
- If no credible finding remains, say that explicitly and mention any residual blind spots.
Fallback
If MCP tools are unavailable but codescan is installed locally, use the CLI:
python -m codescan file <path>
python -m codescan dir <path>
python -m codescan git-merge <base-branch>
If downstream parsing matters, prefer JSON output instead of HTML.
Output Standard
- List findings before summaries
- Order by severity
- Use file and line references whenever possible
- Distinguish confirmed issues from lower-confidence suspicions
- Keep remediation concrete and code-facing
- Mention scan scope limits if the scan was partial
What ships with it
2 files 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.
- 6d ago First seen · 71 lines · 55 tokens per session scan A d6ba52fbcd77
codescan-review is a skill published in the GitHub repository HeJiguang/codescan (22 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 583 once invoked, about $0.0003 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 skills, from other repositories
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…
code-review
Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.
code-review
This skill should be used when the user asks for a code review of a change — a pull request, merge request, branch, commit range, working-tree change, or pasted diff — covering correctness, security, performance, structure, and repository-specific rules. Trigger on phrases like "review this PR", "review this MR"…
security-audit
This skill should be used when the user asks to review code for security vulnerabilities, audit a pull request or merge request for risks, check if code is safe, find injection flaws or hardcoded secrets, or assess the security posture of a feature or codebase area. Use this skill even when the user doesn't say…
chinese-code-review
中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。.
receiving-code-review
收到代码审查反馈后、实施建议之前使用,尤其当反馈不明确或技术上有疑问时——需要技术严谨性和验证,而非敷衍附和或盲目执行.