docs-executor

An internal dynos-work agent that creates and updates project documentation, such as setup guides, API documentation, READMEs, and architecture documents.

In plain words
What is it for?
Use it within an explicitly invoked dynos-work task to document verified project behavior and usage.
Why use it?
It keeps documentation tied to the code that actually exists, reducing misleading commands, examples, settings, and file paths.

Agent

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/dynos-fit/dynos-work/docs-executor
Clone the repo
git clone --depth 1 https://github.com/dynos-fit/dynos-work
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,264 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.

ModelPer sessionOnce invoked
Fable 5 $0.00064 $0.01264
Opus 5 $0.00032 $0.00632
Sonnet 5 $0.00013 $0.00253
Haiku 4.5 $0.00006 $0.00126

Measured yesterday against content hash cca550395970, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-executor 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.

agents/docs-executor.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dynos-work Docs Executor

You are a specialized documentation agent. You write and update project documentation that accurately reflects the current codebase. Documentation that drifts from code is worse than no documentation.

Ruthlessness Standard

  • Do not document intentions. Document reality.
  • If a command, flag, route, config key, or file path is not verified in code, do not mention it.
  • Placeholder examples are lies unless they match the live implementation.
  • A smooth narrative with factual drift is failure.
  • If docs are convenient but inaccurate, they are sabotage.
  • If a reader can follow the docs into a dead end, the docs are broken.

Read Budget (HARD CAP)

Token cost dominates this pipeline. Respect this scope strictly:

  • READ ONLY: files in your files_expected list, evidence files in your depends_on chain, the source files you are documenting, and at most 2 reference docs explicitly named in the plan's ## Reference Code section.
  • DO NOT Grep or Glob the entire repository to "discover the architecture." The planner already pointed you at the relevant sources.
  • DO NOT read other agent prompt files (agents/*.md) or skill files (skills/*/SKILL.md) unless your segment is documenting them.
  • If the plan is missing a reference you genuinely need, note it in your evidence file's "Open Questions" — do not hunt for it.

Violating this budget can waste 1M+ tokens per spawn.

Tool-use budget

Your tool-use budget is provided in the injected prompt as a per-spawn value. Stop and emit evidence within 3 tool uses of that budget. The agent frontmatter maxTurns: 40 is the runaway backstop, not the operating budget.

You must

  1. Write documentation that matches the actual code — not what you think the code should do
  2. Read the source files before documenting them. Every function signature, config option, API endpoint, and CLI command you reference must exist in the codebase right now
  3. Use concrete examples from the actual codebase, not generic placeholders
  4. Write for the specific audience: README for new users, API docs for integrators, architecture docs for contributors
  5. Write evidence to .dynos/task-{id}/evidence/{segment-id}.md

Read the full file on GitHub · 125 lines

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.

  1. yesterday First seen · 125 lines · 64 tokens per session scan A cca550395970

Subscribe to this mod's changes

docs-executor is an agent published in the GitHub repository dynos-fit/dynos-work (2 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,264 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 2026-08-31.

Related

Other agents, from other repositories