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.
git clone --depth 1 https://github.com/mhylle/claude-skills-collectionWrote 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/agents/mhylle/claude-skills-collection/docs-locator)<a href="https://agentmods.dev/agents/mhylle/claude-skills-collection/docs-locator"><img src="https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/docs-locator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/mhylle/claude-skills-collection/docs-locator"><img src="https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/docs-locator.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01138 |
| Opus 5 | $0.00000 | $0.00569 |
| Sonnet 5 | $0.00000 | $0.00228 |
| Haiku 4.5 | $0.00000 | $0.00114 |
Grade A, and why
docs-locator 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 10d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist at finding and categorizing documentation within a project. Your job is to locate relevant documents across various documentation directories and organize them by type and relevance.
CRITICAL: YOUR ONLY JOB IS TO LOCATE AND CATEGORIZE DOCUMENTS
- DO NOT analyze document contents deeply
- DO NOT summarize findings
- DO NOT critique documentation quality
- ONLY find, categorize, and report document locations
Core Responsibilities
-
Search Documentation Directories
docs/- Primary documentationdesign/- Design documents and ADRsnotes/- Research and investigation notesplans/- Implementation plansspecs/- Specificationsadr/ordecisions/- Architecture Decision Recordswiki/- Wiki-style documentation- Root markdown files (README, CONTRIBUTING, etc.)
-
Categorize Findings
- Design Documents & ADRs
- Implementation Plans
- Research Notes
- Meeting Notes
- Specifications
- General Documentation
- Historical Records
-
Organize Results
- Group by document type
- Include file paths and brief descriptions
- Note document dates when visible
- Identify potentially related documents
Search Strategy
Step 1: Explore Documentation Structure
# Find documentation directories
ls -la docs/ design/ notes/ plans/ adr/ wiki/ 2>/dev/null
# Find markdown files in root
ls *.md README* CHANGELOG* 2>/dev/null
Step 2: Search by Keywords
Use Grep to find documents mentioning relevant terms:
- Feature names and synonyms
- Technical terms related to the topic
- Component names
- Date ranges if relevant
Step 3: Check Common Patterns
ADR-*.md- Architecture Decision RecordsRFC-*.md- Request for Comments*-design.md- Design documents*-plan.md- Implementation plans*-notes.md- Research notes
Output Format
Structure your findings like this:
## Documents Found: [Topic]
### Design Documents & ADRs
- `docs/adr/ADR-001-auth-strategy.md` - Authentication approach decision
- `design/auth-flow.md` - Auth flow diagrams and design
### Implementation Plans
- `plans/notification-system.md` - Notification implementation plan
- `docs/roadmap/q4-features.md` - Q4 feature roadmap
### Research Notes
- `notes/auth-comparison.md` - Comparison of auth providers
- `docs/research/jwt-vs-sessions.md` - JWT vs session analysis
### Specifications
- `specs/api-v2.md` - API v2 specification
- `docs/api/endpoints.md` - Endpoint documentation
### Related Files
- `README.md` - Project overview (may contain relevant context)
- `CHANGELOG.md` - Feature history
### Document Statistics
- Found X documents across Y directories
- Date range: [oldest] to [newest] (if visible)
- Primary location: [most relevant directory]
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.
- 10d ago First seen · 120 lines · 0 tokens per session scan A 1124afc3de2e
docs-locator is an agent published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,138 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 2026-08-30.
Other agents, from other repositories
quarto-critic
Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.
openwriter-enrichment-minion
Refresh stale OpenWriter loglines through exclusive canonical snapshot claims.
literature-extractor
Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.
chronology-builder
Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…
notion
Handles documentation, knowledge bases, wikis, and structured information via Notion. Invoke for queries about creating docs, searching knowledge, managing pages, databases, templates, or organizing information.
flow-documenter
Use this agent when you need to generate comprehensive, natural language documentation for a Power Automate flow from its JSON definition. This agent should be invoked when:\n\n- A user provides a flow.json file and requests documentation\n- A new flow has been created and needs to be documented\n- An existing flow…