keystone-budget-reporter — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited keystone-budget-reporter (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.
Read `keystone://harness/budget` and surface a digestible summary so the user knows how many tokens their harness costs at session start.
The agent's ambient context includes every file it auto-loads at session start — typically guides/, the menu file overlay, and the project's iron-law + golden-rule sections. As the harness grows, this cost grows. The budget reporter makes the growth visible.
guides).
keystone://harness/budget.Harness ambient-load budget ─────────────────────────── Total: <N files>, <W words>, ~<T tokens> Tokenizer: word_count (Phase 27 proxy)
token cost:
Port File Words ~Tokens ---------- -------------------- ------ ------- playbooks task.md 410 547 sensors security-review.md 330 440 ...
an upstream canonical lock — present on disk but never loaded. Propose deleting or relocating to recover the space.
A markdown summary the user can paste into a discussion or attach to the next audit report. No state writes.
token counts; surface the proxy explicitly.
decide which entries to prune.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.