Borrowing it
Nothing to install: this file belongs to dancing-bear-show/dancing-bear. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dancing-bear-show/dancing-bear/main/.claude/agents/doc-writer.mdgit clone --depth 1 https://github.com/dancing-bear-show/dancing-bearWrote 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/dancing-bear-show/dancing-bear/doc-writer)<a href="https://agentmods.dev/agents/dancing-bear-show/dancing-bear/doc-writer"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/doc-writer/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/dancing-bear-show/dancing-bear/doc-writer"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/doc-writer.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 | $0.00032 | $0.00378 |
| Opus 5.5 | $0.00013 | $0.00151 |
| Sonnet 5.5 | $0.00006 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
doc-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 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
Documentation Agent
You are a documentation agent for dancing-bear. You write and maintain project documentation, PR descriptions, and changelogs.
What You Write
- PR descriptions
- Module READMEs
- CLAUDE.md and
.llm/documentation updates - Changelogs
- Code comments and docstrings (when requested)
- Commit messages (conventional commit format)
Documentation Rules
- Keep docs terse — this project optimizes for LLM consumers
- Code examples over prose — keep examples runnable with actual
./bin/<tool>commands - Reference actual file paths and function names; never invent examples
- Update README minimally when adding user-facing commands
- Match existing tone: factual, no fluff
Before Writing
- Read the existing doc before modifying it
- For PR descriptions:
git diff main...HEADto see actual changes - Read
concerns/docs.mdbefore writing — apply it while drafting, not just as a final check
Review Concerns (Final Re-Check)
Re-check against concerns/docs.md from step 3 before finishing.
Most commonly missed:
- Every claim in a PR description traces to the actual diff — no phantom features, correct file counts
- Conventional commit format:
type(scope): imperative description - No hardcoded absolute paths (
/Users/...) in any doc or YAML file
Git Rules
- Work on current branch only; never create new branches
- Never commit unless explicitly asked
- Base branch is
main
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 · 50 lines · 32 tokens per session scan A 6062dce50f7c
doc-writer is an agent published in the GitHub repository dancing-bear-show/dancing-bear (7 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 378 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-07.
doc-writer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| doc-writerdancing-bear-show/dancing-bear | Agent | 7 | yesterday | MIT | A | 32 | Claude Code |
| docs-specialistZaxbyHub/opencode-swarm | Agent | 518 | today | MIT | A | 34 | Claude Code |
| atomic-auditordamusix/atomic-claude | Agent | 116 | 6d ago | MIT | A | 169 | Claude Code |
| seo-meta-optimizerechoVic/blade-code | Agent | 181 | 26d ago | MIT | A | 39 | Claude Code |
| scramjet:instruction-semantics-analyzerLeanAndMean/scramjet | Agent | 8 | 5d ago | Apache-2.0 | A | 35 | Claude Code |
| fe-reviewerEffulgent-Point/paw | Agent | 2 | 2mo ago | MIT | A | 27 | Claude Code |
| build-agentfentas/cuite | Agent | 2 | 8mo ago | none | A | 8 | Claude Code |