菜单
Run `brief --json` to produce a structured overview of the repository. Used by other skills as orientation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Map distinct externally reachable input-processing subsystems into focus areas for the threat-model skill to carry into later security audits. This is a short, read-only orientation pass, not a vulnerability scan.
Derive a project's security contract from its source and docs, then emit it as structured data other skills can cite. Records what the project assumes about callers and inputs, what properties it claims and disclaims, which code is out of scope, and which recurring tool findings are known-safe. This is not a vulnerability scan; it produces the trust map that security-deep-dive loads instead of re-deriving boundaries per run.
Default pipeline scrutineer runs when a repository is added. Triggers a standard set of other skills in parallel, then writes a short summary of what was enqueued. Edit the list below to change the default scan coverage without touching scrutineer's Go code.
Audit first-party source for security vulnerabilities using an inventory-first, six-step per-sink methodology. Use when you want a thorough scan that distinguishes real findings from pattern matches and records both in a machine-readable report. The target is this codebase's own code, not its dependencies.
Compare open findings in one repository and record how they relate. Marks same-vulnerability findings as duplicates, findings that another finding's fix will close as subsumed, and findings that combine into a higher-severity attack as a chain.
High-recall static source-code vulnerability scan adapted from Anthropic's defending-code reference harness. Fans out by focus area, ranks candidates by confidence, and emits Scrutineer findings for later verification.
| name | repo-overview |
| description | Run `brief --json` to produce a structured overview of the repository. Used by other skills as orientation. |
| license | MIT |
| compatibility | Requires the `brief` CLI (https://github.com/git-pkgs/brief) on PATH. |
| metadata | {"scrutineer.model":"mid","scrutineer.version":1,"scrutineer.output_file":"report.json","scrutineer.output_kind":"repo_overview"} |
Produce an overview of the repository cloned at ./src by invoking the brief tool and writing its output verbatim as the report. brief already does the reading, summarising, and structured-output work; this skill is the thin harness around it.
./src — the cloned repository./context.json — read scrutineer.scan_subpath; other fields are unused./report.json — write the final report hereIf ./context.json has scrutineer.scan_subpath set, run brief against that sub-folder instead of the repo root:
brief --json ./src/$(jq -r '.scrutineer.scan_subpath // ""' ./context.json | sed 's:^/*::') > ./report.json
If scan_subpath points at a directory that does not exist under ./src, write {"error": "scan_subpath not found: <path>"} and stop. For a root scan (no scan_subpath), the command reduces to:
brief --json ./src > ./report.json
That is the whole workflow. If brief exits non-zero (including when it is missing), read its stderr and write a short {"error": "..."} JSON document to ./report.json so the caller can see what went wrong rather than getting an empty file. Do not post-process brief's output; the consumer expects its native schema. Do not try to install brief; it is pinned by the deployment.