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 agentmods add skills/theagenticguy/agentic-plugins/audit-skillnpx skills add theagenticguy/agentic-plugins --skill audit-skillgit clone --depth 1 https://github.com/theagenticguy/agentic-pluginsWhat 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 | $0.00094 | $0.00719 |
| Opus 5 | $0.00047 | $0.00360 |
| Sonnet 5 | $0.00019 | $0.00144 |
| Haiku 4.5 | $0.00009 | $0.00072 |
Grade A, and why
audit-skill 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 2d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contents
| Reference | When to load |
|---|---|
../../references/rubric.md |
The scoring rubric (shared) |
../../references/write-protocol.md |
Write discipline |
templates/scorecard-skeleton.md |
Output file shape |
Audit a skill
Score one skill against the 7-dimension rubric. The skill is the input; a scorecard Markdown file is the output.
How it works
- Resolve
{{ skill }}to an absolute path. Accept either a directory path (skills/research) or a bare skill name (research) — glob for the matchingSKILL.md. - Read the rubric at
${CLAUDE_PLUGIN_ROOT}/references/rubric.md. - Read the skill in full: SKILL.md, every file under
references/, every file undertemplates/. The scorecard is grounded in what's in the files, not in the description alone. Reading is the primary work. - If a prior
/gardeneraudit exists atplugin-gardener/audit/, read its latestcollisions.csvandclusters.csvfor cross-reference context. Collisions involving this skill inform Dimension 1 (description quality) and Dimension 5 (proactive-label discipline) — check whether the description carries the right negative-keyword discriminators. For every collision row, open the sibling SKILL.md and verify by reading, not from the cosine alone. - Write a scorecard to
plugin-gardener/audit/ad-hoc/<skill-name>-<YYYY-MM-DD>.mdusingtemplates/scorecard-skeleton.md. - Present the total, dimension scores, and top-3 recommended actions inline.
Apply the rubric dimension by dimension. Record a short rationale (1–2 sentences with a file:line citation from the files you read) for every criterion scoring under 3 points. The rationale is the value; the number is the aggregate.
On the role of embedding data: collisions and clusters from a prior /gardener run are binoculars, not the photograph. They point you at the right cross-references to open. Verify every flagged collision by reading both SKILL.md files — a high cosine is an invitation to investigate, not a verdict.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 55 lines · 94 tokens per session scan A 8984f4cb1f37
audit-skill is a skill published in the GitHub repository theagenticguy/agentic-plugins (5 stars, last pushed 21d ago), licensed MIT. It adds 94 tokens to every session and 719 once invoked, about $0.0005 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
genesis
Use this skill BEFORE drafting any agentic primitive module (skill, persona scoping file, scope-attached rule file, orchestrator workflow) or when refactoring an existing one. Activate whenever the task asks to design, restructure, or critique an agentic module across any agent harness (Claude Code, Copilot, Cursor…
genesis-evals
Use this skill to run the genesis maintainer-side eval suite against a target model (default: claude-opus-4.7). Activate when validating a genesis PR, when changing the genesis catalogue (architectural-patterns, primitives, design-patterns, refactor-patterns, composition-substrate, pattern-tradeoffs, SKILL.md), or…
agents
Guidance for AI coding agents working on the adeptability (adept) codebase. Humans: see README.md for usage and CONTRIBUTING.md for the contributor workflow.
using-adept
Use the adept CLI to author AI skills once and render them into Claude Code, Cursor, Codex, Copilot, and OpenCode. Apply when installing/syncing skills, editing skill.yaml/SKILL.md, or touching .adeptability/.
authoring-adept-agents
Write a good, portable adept agent (subagent): trigger-shaped description, one job per agent, generator/evaluator separation, explicit boundaries, restricted tools. Apply when creating or editing an agent file or running adept agent add.
authoring-adept-loops
Compose a loop — a scheduled system that discovers work, hands it to agents, verifies with an independent evaluator, persists state, and reschedules itself. Apply when the user wants automation that runs on a timer, a triage/babysitter routine, or asks about adept loop add.