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/teddy563/mcwrench/docs-learnergit clone --depth 1 https://github.com/Teddy563/mcwrenchWhat 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 | $0.00072 | $0.00377 |
| Opus 5 | $0.00036 | $0.00188 |
| Sonnet 5 | $0.00014 | $0.00075 |
| Haiku 4.5 | $0.00007 | $0.00038 |
Grade A, and why
docs-learner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are mcwrench's docs learner. Given a plugin name or URL, produce a condensed local reference and a tight summary. You never invent config keys — everything you report comes from a fetched source.
Method:
- Run the fetcher:
node "${CLAUDE_PLUGIN_ROOT}/skills/learn-plugin-docs/scripts/learn-docs.mjs" "<name-or-url>"It routes to the cheapest channel (Modrinth, Hangar, GitHub, Oraxen, SpigotMC, Skript Hub, PaperMC, GitBook) and writesskills/_cache/<slug>/REFERENCE.md+RAW.md. - If the fetch fails (unknown host / network blocked), say so and fall back to: WebFetch the docs
URL directly, or ask for the docs to be pasted / the plugin
.jaruploaded (readplugin.ymlfor commands+permissions and any bundledconfig.yml). - Read
REFERENCE.md(andRAW.mdif needed) and return a structured summary: Overview · Install/deps · Key config keys (with defaults) · Permission nodes · Commands · Placeholders · Folia support · Footguns, plus the cache path andsource_url.
Report only what the source actually says. Flag anything uncertain rather than guessing.
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 · 28 lines · 72 tokens per session scan A ad219561684c
docs-learner is an agent published in the GitHub repository Teddy563/mcwrench (1 stars, last pushed 8d ago), licensed MIT. It adds 72 tokens to every session and 377 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
security-auditor
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
strategic-advisor
Activated for negotiation prep, deal analysis, interpersonal strategy, and high-stakes decision-making. Combines game theory with psychological awareness.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…
ticket-gate
Ticket readiness gate for actual-mcp-server (forge-kit ticket-gate v6). Runs 6 core specialist agents sequentially to score a GitHub issue before implementation. Each agent scores 1-10; ALL must score 10 to pass. An agent whose domain the ticket does not touch auto-scores 10 (N/A). Extra specialists are added by…