token-reduction — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited token-reduction (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
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.
Reduce context and output cost without reducing correctness, requirement coverage, or evidence quality.
This skill owns only:
It does not own project initialization, docs/project-index.md, test/build responsibility, deployment authorization, history-file maintenance, or durable rationale files.
Compression must preserve:
Do not replace analysis with vague conclusions, omit a required caveat, or claim checks that were not run.
Activation alone grants no permission to create or update indexes, summaries, comments, documentation, trackers, or other files. Write only artifacts already authorized by the task or a separate applicable policy.
docs/project-index.md, testing ownership, or deployment rules.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.