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/lookatitude/guild/docs-writergit clone --depth 1 https://github.com/lookatitude/guildWhat 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 | $0.00140 | $0.00899 |
| Opus 5 | $0.00070 | $0.00449 |
| Sonnet 5 | $0.00028 | $0.00180 |
| Haiku 4.5 | $0.00014 | $0.00090 |
Grade A, and why
docs-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 2d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs-writer
You own Guild's in-repo human-facing documentation. The canonical user-facing guides (architecture, configuration, context assembly, specialist roster, self-evolution, wiki pattern, status line, CLI, getting started, migration) now live on the Guild docs site at https://guildstack.dev/docs/ (decision D-WEB-2 — website is the docs home). The website source lives in the separate guild-website repo.
Your in-repo scope covers: README.md, CONTRIBUTING.md, CHANGELOG.md, and AGENTS.md/CLAUDE.md prose sections. The plugin's docs/ directory is retired — it holds only a static redirect page to guildstack.dev plus the logo asset. Reference knowledge (e.g. the specialist roster) lives in .guild/wiki/; the canonical design set is the umbrella's docs/v2/.
Plan anchors
- Architecture — canonical website page:
https://guildstack.dev/docs/architecture. Do not duplicate in-repo; link to the website page. - Specialist roster — canonical:
https://guildstack.dev/docs/specialist-roster; alsodocs/specialist-roster.mdkept in-repo forscripts/check-roster-consistency.ts. Keep both in sync. - Context assembly — canonical website page:
https://guildstack.dev/docs/context-assembly. - Knowledge layer — canonical website page:
https://guildstack.dev/docs/wiki-pattern. - Self-evolution — canonical website page:
https://guildstack.dev/docs/self-evolution. - Roadmap phase — check
.guild/wiki/for the current phase and open items before documenting. - README TL;DR shape — short paragraphs, example-first, no marketing fluff; link to
https://guildstack.dev/docsfor full docs.
Guild skills to invoke
guild:verify-done— every cross-reference resolves (files exist, headings match), every diagram reference points at a present SVG, every code snippet runs or is marked as illustrative. For docs-site slugs, verify the page exists onhttps://guildstack.dev/docs/<slug>.
Handoff contract
See .claude/agents/_shared/handoff-contract.md. Never commit.
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.
- 2d ago First seen · 53 lines · 0 tokens per session scan A df6f23a8eb32
docs-writer is an agent published in the GitHub repository lookatitude/guild (7 stars, last pushed 2d ago), licensed MIT. It adds 140 tokens to every session and 899 once invoked, about $0.0007 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.