Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ngreenwall/claude-skills --skill token-auditgit clone --depth 1 https://github.com/ngreenwall/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ngreenwall/claude-skills/token-audit)<a href="https://agentmods.dev/skills/ngreenwall/claude-skills/token-audit"><img src="https://agentmods.dev/badge/skills/ngreenwall/claude-skills/token-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ngreenwall/claude-skills/token-audit"><img src="https://agentmods.dev/badge/skills/ngreenwall/claude-skills/token-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00143 | $0.03184 |
| Opus 5 | $0.00072 | $0.01592 |
| Sonnet 5 | $0.00029 | $0.00637 |
| Haiku 4.5 | $0.00014 | $0.00318 |
Grade A, and why
token-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Token Audit
A token-bloat audit over instruction and config prose and this repo's skill architecture. Recognized targets: SKILL.md files, CLAUDE.md, your global context file (the standing instructions your AI tool loads every session, e.g. ~/.claude/CLAUDE.md), README.md, slash command files (.claude/commands/*.md), and other instruction/config prose files.
This is NOT:
- qa-audit, that reports bug-shaped findings to fix. This skill proposes token-reduction actions (rewrite, split, merge, add nav, remove) instead, a different output shape.
- drift-check, that verifies global context actually loaded and is being followed in a live session. This skill is a static audit, session state doesn't matter.
- A code minifier. This skill never touches code, only instruction/config prose and skill structure.
- A fix for
docs/WORKLOG.mdordocs/PROJECT.mdbloat. Those are logs governed byhandoff's own per-entry length caps and archive thresholds, not this checklist.
Modes
Mode A - single file (default). One file given, run the single-file checklist only.
Mode B - full library. Explicitly requested (e.g. "audit the whole skills library"). Runs the single-file checklist across every file, plus the cross-file checklist and the unused-skills question. This is the expensive path, only run when asked.
Mode C - refresh guidance. Explicitly requested (e.g. "check for updated Anthropic guidance," "refresh the checklist"). Requires WebFetch; if it's unavailable in this environment (e.g. blocked by org policy), tell the user and stop rather than proceeding without it. WebFetch these Anthropic doc pages: https://docs.claude.com/en/docs/build-with-claude/prompt-engineering/overview and https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents. Compare their current guidance against the Checklist section below, then propose specific additions/edits/removals to the Checklist for confirmation, same before/after format as Step 6. This mode only edits this skill file, never a target file. Skip prompt-caching guidance, already out of scope (see "Dropped, not checked" below).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 157 lines · 143 tokens per session scan A a3c8d758fc83
token-audit is a skill published in the GitHub repository ngreenwall/claude-skills (2 stars, last pushed 9d ago), licensed MIT. It adds 143 tokens to every session and 3,184 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sdd-apply
Skill "sdd-apply" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, purpose, what you receive and execution and persistence contract.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
sdd-verify
Skill "sdd-verify" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, activation contract, hard rules and decision gates.
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-spec
Write SDD delta specs with requirements and scenarios. Trigger: orchestrator launches spec work for a change.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.