classmap-target — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited classmap-target (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use CLASSMAP.md to choose candidate code, then verify its responsibilities in the current source.
The result should explain where to look first and any boundary that matters to the request. Locating responsible code does not by itself establish a bug's root cause.
classmap-maintain when requested. Do not make it a prerequisite for the current task.CLASSMAP.md to select candidates. If the map is missing, briefly say so and use focused search for this task; do not create it.An absent map entry is not evidence that the behavior is absent from the project.
Follow relevant entrypoints, callers, and implementations; search within the likely module, then use repository-wide targeted search if the location is still unresolved. Use request clues and code evidence as search terms. Skip a narrower step when there is no useful module or candidate to start from.
Avoid aimless repository exploration. A precise repository-wide search can be appropriate even when a map exists. Stop expanding once the relevant responsibility is sufficiently supported by code; no fixed file or search-count budget is required.
If the responsible code cannot be confirmed, report what was checked and what remains unresolved rather than presenting a guess as verified.
Name the primary file or files and explain the responsibility verified in code. Add relevant symbols or locations when useful. Include related files only with a reason or condition for inspecting them. Mention excluded candidates only when they resolve a real ambiguity.
Keep the format proportional to the request. For example, after checking the relevant code:
- Start with `src/auth/LoginService.ts`: its login flow coordinates credential checks and failed-login policy.
- Also inspect `src/auth/AuthController.ts` if request or response fields change; it owns the HTTP contract.Do not generate empty primary/secondary/excluded sections or a search-budget report. Separate verified responsibilities from unresolved candidates; describe the specific missing evidence instead of assigning confidence scores.
After an implementation task, update an existing CLASSMAP.md only when verified facts in the task's scope would otherwise cause a future agent to look in the wrong place, miss an entrypoint, or misunderstand a responsibility:
Adding routine helpers or tests, changing an internal dependency, or fixing behavior within an unchanged responsibility does not by itself require an update.
Update only affected entries whose facts were verified during this task, including obsolete paths confirmed through the move or deletion. Preserve the existing useful layout and manual notes; do not migrate formats or rebuild the map. Use feature/change cues, code paths, and concise responsibilities, adding boundaries only where helpful.
Report drift outside the task's scope without fixing it. When the map is missing or needs broader maintenance, suggest classmap-maintain as a separate task and continue the current work without that dependency.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.