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 commands/rana/skills/integritygit clone --depth 1 https://github.com/rana/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/commands/rana/skills/integrity)<a href="https://agentmods.dev/commands/rana/skills/integrity"><img src="https://agentmods.dev/badge/commands/rana/skills/integrity.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00778 |
| Opus 5 | $0.00000 | $0.00389 |
| Sonnet 5 | $0.00000 | $0.00156 |
| Haiku 4.5 | $0.00000 | $0.00078 |
Grade A, and why
integrity 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 4d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify the cognitive toolkit's internal consistency and memory accuracy. The toolkit makes claims about its own structure, and memory makes claims about the world. This command checks both.
$ARGUMENTS
Test Suite
1. Structural Integrity
Run /catalog to build the full skill inventory. Then verify:
- Skill count in CLAUDE.md, SYSTEM.md, and plugin.json matches actual
skills/*/SKILL.mdcount - Command count matches actual
commands/*.mdcount - Every skill referenced in SYSTEM.md selection matrix exists
- Every skill referenced in composition examples exists
- Stage map covers all skills (no orphans)
- Finding Shape Convention in CLAUDE.md lists the correct skills
2. Skill Anatomy Compliance
For each skills/*/SKILL.md:
- Frontmatter has
name,description,argument-hint namein frontmatter matches directory name- Output section exists with skill-specific guidance
- Skills claiming to produce standard finding shape actually instruct that format
- Cognitive/creative skills that shouldn't produce finding shape don't claim to
3. Cross-Reference Integrity
Run /doc-health scoped to the toolkit's own documents (CLAUDE.md, SYSTEM.md, plugin.json):
- Every skill name in SYSTEM.md maps to a
skills/<name>/directory - Composition topology (affinities, terminal skills, dead zones) references only existing skills
- Quick reference section references only existing skills
- No stale references to deleted skills
4. Composition Coherence
For each composition example in SYSTEM.md:
- All named skills exist
- Ordering follows stated principles (perception-expanding before analytical, simplification last)
- No examples violate stated dead zones
- Terminal skills appear only at chain end
5. Document Consistency
- CLAUDE.md and SYSTEM.md agree on: skill counts, command counts, skill classification (analytical vs mission vs cognitive)
- Plugin.json description matches CLAUDE.md opening paragraph
- Calibrate parameters documented in SYSTEM.md match
commands/calibrate.md - Environment contract tables are consistent between CLAUDE.md and SYSTEM.md
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.
- 4d ago First seen · 71 lines · 0 tokens per session scan A 01a5bd5f554d
integrity is a command published in the GitHub repository rana/skills (1 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 778 tokens. 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 commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
show
Show this project's saved Recall context (.recall/context.md).
coding-drill
Rapid-fire reps — pattern recognition, complexity-of-this-snippet, template recall — flashcard cadence; prioritizes your weak patterns.
init
Bootstrap project context (project.intent.md and project.glossary.json) from an existing codebase using deterministic scan + LLM synthesis + interactive editing. Use --harness to scaffold additional repo-level harness docs.
ai-act-ask
Answer an EU AI Act question grounded in the bundled knowledge base — verbatim statute text, obligation paraphrases, and the compound-risk taxonomy. Offline and deterministic by default; cites the articles it relies on.
check
Is the context layer still true? 0-token staleness + broken-citation audit (no LLM, CI-friendly). Add --status for the fast hash-only subset.