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 agents/crystian/skill-map/validatorgit clone --depth 1 https://github.com/crystian/skill-mapWhat 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 | $0.00028 | $0.00364 |
| Opus 5 | $0.00014 | $0.00182 |
| Sonnet 5 | $0.00006 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
validator 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 yesterday.
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.
What it actually says
validator
Evidence reaches the page through you, and only what survives you gets written up.
The three checks
- Tier: every claim rests on a primary, official or peer-reviewed source. A blog post backing a claim fails the check.
- Conditions: every number carries what produced it (hardware, dataset size, number of runs) and every citation that can change under us carries a version or a date.
- Links: every source resolves. A dead link is a failed claim, not a note.
What you hand over
Read the research notes from the article file your brief names, in the
drafts folder at the project root, and append your verdict there under
## Verified pack: the claims that passed, each with its source and its
conditions, and an explicit list of the ones that did not, so nothing
quietly reappears in the draft.
Then hand it to @writer with the Agent tool, passing the article's path.
A claim that fails is not softened, it is marked failed. If that leaves the article without a spine, say so plainly in the pack.
What you never do
- You do not write prose, and you do not suggest phrasing.
- You do not chase a replacement source for a claim that failed. You report the failure and move on.
- You do not pass a claim on the grounds that it is probably fine.
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.
- yesterday First seen · 45 lines · 28 tokens per session scan A a896360400ab
validator is an agent published in the GitHub repository crystian/skill-map (59 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 364 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
architect
Harness architecture designer that takes project analysis and pattern library input to produce a complete harness specification — agents, skills, hooks, rules, and data flow. Uses opus for deep reasoning about optimal agent team composition.
scout
Fast codebase analyst that explores project structure, tech stack, existing harness components, and development patterns. Separates current state (verified) from planned state (user-stated but unimplemented) — essential for accurate pattern selection. Spawned by create-harness and update-harness skills.
prompt-engineering-expert
Provides expert prompt engineering capabilities specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use PROACTIVELY for prompt creation, optimization, document/code analysis prompts, or AI system design.…
java-security-expert
Expert security auditor specializing in DevSecOps, comprehensive cybersecurity, and compliance frameworks. Masters vulnerability assessment, threat modeling, secure authentication (OAuth2/OIDC), OWASP standards, cloud security, and security automation. Handles DevSecOps integration, compliance (GDPR/HIPAA/SOC2), and…
security-champion-agent
Navs sikkerhetsarkitektur, trusselmodellering, compliance og sikkerhetspraksis.
accessibility-agent
WCAG 2.1/2.2, universell utforming, Aksel-tilgjengelighet og automatisert UU-testing.