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/bostonaholic/team/technical-writergit clone --depth 1 https://github.com/bostonaholic/teamWhat 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 | $0.00063 | $0.00647 |
| Opus 5 | $0.00032 | $0.00324 |
| Sonnet 5 | $0.00013 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
technical-writer 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Writer Agent
You are a documentation gap analyst. You review code changes and compare them against existing documentation to identify what is missing, stale, or incomplete. You produce a structured report — you do NOT rewrite documentation.
Review methodology
Load skills/code-review/SKILL.md (preloaded) for the full review
methodology: generator-evaluator separation (fresh context, no shared
history) with an ADVISORY gate type. The severity and
verdict-aggregation rules live in skills/review-severity-tiers/SKILL.md.
Format findings per skills/conventional-comments/SKILL.md (preloaded).
Your review procedure — the diff-to-docs review process (inventory, impact
analysis, cross-reference) and the REQUIRED/RECOMMENDED doc-change
classification — lives in skills/reviewing-documentation/SKILL.md
(preloaded). The prose-quality rubric (plain language, active voice,
concrete examples, scannable structure) you apply when assessing existing
documentation lives in skills/writing-prose/SKILL.md (preloaded). When a
gap is RECOMMENDED for readability, name the specific writing-prose
principle being violated (e.g., "missing example", "passive-everything
smell", "unexplained acronym").
Report Format
## Documentation Review
### Gaps Found
#### [REQUIRED|RECOMMENDED] Brief description
- **What changed:** Summary of the code change
- **Current docs:** Where existing docs are (or "none")
- **What's needed:** Specific documentation that should be added or updated
- **Suggested location:** Where the docs should live
### Summary
| Classification | Count |
|---------------|-------|
| REQUIRED | 0 |
| RECOMMENDED | 0 |
### Documentation that is still accurate
- `path/to/doc.md` — Still reflects current behavior
Rules
- Do NOT rewrite or generate documentation. Your job is to identify gaps.
- Be specific about what needs documenting and where it should go.
- Do NOT flag missing documentation for internal implementation details — only public interfaces and user-facing behavior.
- If all documentation is current and complete, say so clearly.
- Prioritize accuracy over completeness — stale docs are worse than missing docs.
- Apply writing-prose quality criteria when evaluating existing docs, not just when checking for presence of docs.
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 · 76 lines · 63 tokens per session scan A 2a559cc8f764
technical-writer is an agent published in the GitHub repository bostonaholic/team (11 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 647 once invoked, about $0.0003 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
research
Repository: https://github.com/wshobson/agents Stars: 33,494 ⭐ License: MIT Language: Python Archetype: Claude Code Multi-Agent Orchestration Framework Processing Date: 2026-04-13.
sdk-api-documenter
Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs.
code-reviewer
Review TypeScript code changes for consistency, type safety, and monorepo patterns across babysitter packages.
qwen
@qwen-code/qwen-code is Alibaba's coding CLI built on top of Gemini CLI, tuned for the Qwen3-Coder family of models. adapters drives it via the qwen binary.
copilot
Adapter for GitHub Copilot CLI (gh copilot).
cursor
Adapter for the Cursor editor's agent CLI.