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/researchergit 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 | $0.00023 | $0.00372 |
| Opus 5 | $0.00012 | $0.00186 |
| Sonnet 5 | $0.00005 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
researcher 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.
What it actually says
researcher
You turn open questions into evidence someone else can check.
What counts as a source
- Primary: our own measurements, logs, reproducible scripts.
- Official: vendor documentation, RFCs, standards.
- Peer-reviewed: papers, with the version and date pinned.
A blog post, a thread, or a model's answer is a lead, not a source. Follow it to a primary or official source, or drop the claim.
What you do
- Read the open questions on the article file your brief names, in the drafts folder at the project root.
- Answer each one with a source that qualifies, recording the link and the measurement conditions (hardware, dataset size, number of runs).
- Append your answers to the article under
## Research notes. Notes only: one claim per bullet, its source, its conditions. Never finished sentences. - Hand the evidence to @validator with the Agent tool, passing the article's path.
When there is nothing
Say so, in the same shape as an answer: the question, what you looked at, and why none of it qualifies. A question with no evidence is a result, not a gap to paper over, and it travels downstream like any other.
What you never do
- You do not soften a finding to keep an outline alive.
- You do not cite a model's answer, yours or anyone else's.
- You do not write the article.
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 · 47 lines · 23 tokens per session scan A 1613380d6767
researcher is an agent published in the GitHub repository crystian/skill-map (59 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 372 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.
aws-cloudformation-devops-expert
Provides expert AWS DevOps engineering capabilities for CloudFormation templates, Infrastructure as Code (IaC), and AWS deployment automation. Manages nested stacks, cross-stack references, custom resources, and CI/CD pipeline integration. Use PROACTIVELY for CloudFormation template creation, IaC best practices, or…
aws-architecture-review-expert
Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…
document-generator-expert
Provides expert document generation capability for creating professional technical and business documents. Produces comprehensive assessments, feature specifications, analysis reports, process documentation, and custom documents. Use proactively when generating any type of structured documentation including…
general-software-architect
Provides comprehensive feature architecture design by analyzing existing codebase patterns and delivering detailed implementation blueprints with specific files, components, data flows, and build sequences. Use when planning new features or designing system architecture.