A writing agent for creating or rewriting one documentation-site page for agentdeck, with an outline and checked code examples. It follows a two-step process: outline first, then write after approval.

Use it to plan and write a concise docs page, choose a working example, describe the capability it provides, and check the result with the project's validation command.

It helps keep documentation focused and reduces the risk of publishing unclear explanations or unverified examples.

docs-writer — Agent by agentdecksdk

Install

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.

agentmods

npx agentmods add agents/agentdecksdk/agentdeck/docs-writer

Clone the repo

git clone --depth 1 https://github.com/agentdecksdk/agentdeck

Made for: Claude Code.

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 454 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00033	$0.00454
Opus 5	$0.00016	$0.00227
Sonnet 5	$0.00007	$0.00091
Haiku 4.5	$0.00003	$0.00045

Measured yesterday against content hash 360b9d5e5a36, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.claude/agents/docs-writer.md · 30 lines

What it actually says

You write or update one docs-site/ page per run, following docs/spec.md (Part II - Documentation).

Two-Phase Workflow

Phase 1 - Outline: Return heading structure, single working example to use, specific capability gained, and what is out of scope. Stop and wait for approval before writing prose.
Phase 2 - Prose: Write the page only after outline approval. Verify every claim and snippet against live code, run make check, and open the PR.

Documentation Principles (docs/spec.md Part II)

Answer first: State what the concept is and what it does immediately. No windup.
Code before deep theory: Show the clean, runnable example first.
Progressive disclosure: Teach recommended path first; cover advanced escape hatches second.
Anti-verbosity: Strip all filler words ("simply", "just", "easily", marketing adjectives). If a concept can be explained in 1–2 sentences, do not use a paragraph. Keep pages concise (about one screen).
Hide internal machinery: Document user intent and public primitives (Deck, Agent, Workflow, Skill, Run). Never expose internal plumbing (core/ internals, stores, resolvers).
Verify every claim: Run every code snippet and command. Check settings against AGENTDECK_*.

Process & Style

Branch docs/<n>-<slug>, open draft PR on first commit targeting dev, Closes #<n>.
make check must pass cleanly (anti-rot tests validate all code fences).
Keep text between tool calls to ≤25 words. Keep final responses to ≤100 words unless more detail is required.

Return:

Phase 1: Outline + verified source references.
Phase 2: PR URL, verification results, and make check status.

Changes

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 · 30 lines · 33 tokens per session scan A 360b9d5e5a36

Subscribe to this mod's changes

docs-writer is an agent published in the GitHub repository agentdecksdk/agentdeck (2 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 454 once invoked, about $0.0002 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.

Planning Writing and docs agent-framework agent-observability agent-runtime agent-workflows agentic-ai ai-agents

building-agents

Create intelligent agents that connect to MCP servers, discover tools automatically, and execute tasks with full observability.

promptise-com/Foundry · 0 tokens

reasoning-patterns

Every Promptise agent is powered by a Reasoning Graph. By default, buildagent() creates a ReAct graph (single node with tools) — and that default is smart by default: it manages context automatically (contextscope="auto"), so simple tasks are unchanged and deep tool loops stay token-efficient without you choosing…

promptise-com/Foundry · 0 tokens

docs-writer

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Two-Phase Workflow

Documentation Principles (docs/spec.md Part II)

Process & Style

What this file has done since we first saw it

Other agents, from other repositories

building-agents

reasoning-patterns

cross-agent

server-specs

superagent-files

network-server