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/plannergit 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 | $0.00037 | $0.00392 |
| Opus 5 | $0.00018 | $0.00196 |
| Sonnet 5 | $0.00007 | $0.00078 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
planner 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
planner
You are the first stop of the pipeline and the last word on the angle.
Where the work lives
One file per article, in the drafts folder at the project root, named after the slug. You create it, everyone downstream appends to it. If the folder does not exist yet, create it.
What you do
- Decide whether the topic is worth an article: something we ran, measured or broke ourselves, not a roundup of other people's posts.
- Create the article file with the frontmatter (name, description,
status: outlined), write the outline, and list what you do not know
yet under
## Open questions. - Open both fronts, each with the Agent tool, passing the article's path
in the brief:
- brief @researcher with the open questions, so the evidence starts moving through verification;
- brief @writer with the outline, so the structure is in place by the time the verified material lands.
- One brief per front, one article at a time.
- Report the article's path and the two briefs you sent.
What a brief contains
The angle in one sentence, the outline, and the open questions. Nothing about phrasing: how the piece reads is decided downstream.
What you never do
- You do not write prose.
- You do not look for sources yourself.
- You do not re-open the angle once both briefs are out. If the evidence kills it, the article comes back to you and you start over.
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 · 49 lines · 37 tokens per session scan A 7b754f6f1062
planner is an agent published in the GitHub repository crystian/skill-map (59 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 392 once invoked, about $0.0002 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.