harness-context — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited harness-context (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 this skill when the user asks about Open Harness layout, lifecycle, conventions, git workflow, or where files live.
CLAUDE.md for the orchestrator contract — what the root-levelagent does and does not do.
README.md files (e.g.apps/README.md, crons/README.md, tasks/README.md, scripts/README.md, .worktrees/README.md) and the Project Structure section of CLAUDE.md. There is no single comprehensive tree — use the filesystem and the directory READMEs.
.claude/rules/:git.md — issue / branch / commit / PR conventionssandbox-processes.md — tmux sessions for long-running processesdirectory-readme.md — when a directory needs a READMEadvisor-model.md — pattern for delegating to sub-agentspath:line citations.section of CLAUDE.md.
.claude/rules/.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.