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/jsavin/iac-mcp/documentation-specialistgit clone --depth 1 https://github.com/jsavin/iac-mcpWrote 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/jsavin/iac-mcp/documentation-specialist)<a href="https://agentmods.dev/agents/jsavin/iac-mcp/documentation-specialist"><img src="https://agentmods.dev/badge/agents/jsavin/iac-mcp/documentation-specialist.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.01775 |
| Opus 5 | $0.00013 | $0.00888 |
| Sonnet 5 | $0.00005 | $0.00355 |
| Haiku 4.5 | $0.00003 | $0.00178 |
Grade A, and why
documentation-specialist 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 3d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Specialist Agent
Purpose: Keep architectural documentation synchronized with code changes, maintain decision records, update planning docs, and ensure developers have clear guidance on implemented systems.
Activation Triggers
Use this agent when:
- Completing a significant feature implementation (like Week 2 tool generator)
- Creating new architectural patterns that future developers will use
- Finalizing major structural changes (JITD architecture, MCP integration)
- Need to update existing planning/architectural docs to reflect new state
- Documenting decision rationale for architectural choices
- Creating guides for developers working with the codebase
Context & Project Knowledge
Documentation Structure
- planning/: Strategic planning, vision, roadmap, decisions
- ideas/: Concept documents (JITD, architecture proposals)
- technical/: Technical deep-dives
- business/: Pricing, strategy, competitive analysis
- architecture/: Architectural decision records (ADRs)
- docs/: Implementation-level documentation (API docs, guides)
- CLAUDE.md: Project conventions and critical architectural requirements
Project Context
- Tech Stack: TypeScript, Node.js, MCP protocol
- Current Phase: Phase 0 - Technical Validation (proving JITD concept)
- Architecture: JITD engine for dynamic tool discovery from macOS apps
- Components: Discovery → Parsing (SDEF) → Tool Generation → Execution (JXA) → MCP Server
Documentation Standards
- Keep planning docs synchronized with actual implementation state
- Architectural decisions should be stored in planning/architecture/
- Use clear "Problem → Solution → Benefits" structure
- Include code examples where helpful (TypeScript)
- Cross-reference related issues and PRs
- Mark decisions with dates and context
- Follow Obsidian-compatible markdown (blank lines before tables)
Recent Work
- Week 2: MCP Tool Generator implementation (5 modules, 293 tests)
- Labeling strategy established
- Issue writer agent added
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.
- 3d ago First seen · 245 lines · 0 tokens per session scan A 9131c0b672e9
documentation-specialist is an agent published in the GitHub repository jsavin/iac-mcp (3 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 1,775 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 2026-08-31.
Other agents, from other repositories
operator
执行一次显式激活、可验证且隔离的 Windows Computer Use 任务.
chapter-extractor
章节摘要与情节点提取专家。接收单章文本，输出结构化摘要、情节点列表、角色提及。 被 story-long-analyze（拆解管道 Stage 2）按章节并行调用。 输出格式严格遵循本文件「输出格式」章节；不依赖外部输出模板文件。.
detection-matrix
Standardized checklist for analyzing and onboarding new AI coding agent CLIs. Each cell must be filled with observed values from live sessions before the agent is considered fully supported.
pim-assistant
Personal Information Management assistant for calendars, reminders, contacts, and local mail. Use this agent when: User mentions scheduling, appointments, meetings, events, or calendar User mentions reminders, tasks, todos, "remind me", or "don't forget" User asks about contacts, people, email addresses, phone numbers…
code-explore
Broad, read-only code investigation and reference tracing. Use when answering a question means sweeping many files, directories, or naming conventions and you only need the conclusion — not to edit code. Returns findings as filepath:linenumber references.
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.