document-agent

document-agent is a skill for Claude Code from golemfoundation/octant-council-builder. It costs 8 tokens per session (705 once invoked), scanned A, original, MIT.

A documentation generator for council agents, which are automated reviewers in a multi-step evaluation system. It reads an agent definition and related research, then writes a page explaining the agent’s role, process, inputs, outputs, and customization.

In plain words
What is it for?
Use it to create or update `docs/<agent-name>.md` for data-gathering, evaluation, or synthesis agents. It documents their purpose, sources or scoring criteria, workflow, output format, and customization options.
Why use it?
It removes the need to manually turn an agent’s configuration into user-facing documentation. It also keeps the documented process tied to the agent definition and available research.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the council plugin — 11 skills, 10 agents shipped together

Good fit Use it to create or update docs/ .md for data-gathering, evaluation, or synthesis agents. It documents their purpose, sources or scoring criteria, workflow, output format, and customization options.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/golemfoundation/octant-council-builder/document-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.

Any agent
npx skills add golemfoundation/octant-council-builder --skill document-agent
Clone the repo
git clone --depth 1 https://github.com/golemfoundation/octant-council-builder

Made for: Claude Code.

Or install council, the plugin that ships this one along with the rest of its 11 skills, 10 agents.

Wrote 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.

agentmods badge for document-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/golemfoundation/octant-council-builder/document-agent/github.svg)](https://agentmods.dev/skills/golemfoundation/octant-council-builder/document-agent)
Your own site
<a href="https://agentmods.dev/skills/golemfoundation/octant-council-builder/document-agent"><img src="https://agentmods.dev/badge/skills/golemfoundation/octant-council-builder/document-agent/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.

agentmods 80×15 button for document-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/golemfoundation/octant-council-builder/document-agent"><img src="https://agentmods.dev/badge/skills/golemfoundation/octant-council-builder/document-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 705 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00008 $0.00705
Opus 5 $0.00004 $0.00352
Sonnet 5 $0.00002 $0.00141
Haiku 4.5 $0.00001 $0.00071

Measured 10d ago against content hash 292c9eae3354, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

document-agent 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 10d 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.

skills/document-agent/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate Agent Documentation

Create a documentation page for a council agent, covering what it does, how it works, and how to customize it.

Input

$ARGUMENTS is the agent name (e.g., data-audits, eval-governance, synth-debate).

Process

Step 1: Read inputs

Read agents/$ARGUMENTS.md                → agent definition
Read research/$ARGUMENTS.md     → domain context (if exists)

Extract from the agent definition:

  • Name and description (frontmatter)
  • Wave type (from prefix: data/eval/synth)
  • Process steps
  • Dimensions or sources
  • Output format

Step 2: Write documentation

Write docs/$ARGUMENTS.md:

# $ARGUMENTS

**Wave:** [1 — Data Gathering | 2 — Evaluation | 3 — Synthesis]
**Role:** [description from frontmatter]

## What This Agent Does

[2-3 sentences explaining the agent's purpose in plain language. What question does it answer? What data does it produce or what judgment does it render?]

## [Data Sources | Scoring Dimensions | Synthesis Method]

[For data agents: table of sources with URLs and what each provides]
[For eval agents: table of dimensions with descriptions and score calibration]
[For synth agents: description of synthesis methodology]

### [Source/Dimension 1]

[1-2 sentences on what this covers and why it matters]

### [Source/Dimension 2]

...

## Output

The agent writes its output to:
- **Data agents:** `council-out/{project}/data/{name}.md`
- **Eval agents:** `council-out/{project}/eval/{name}.md`
- **Synth agents:** `council-out/{project}/REPORT.md`

### Example Output Structure

[Show the key sections of the output format from the agent definition, condensed]

## Customization

### Changing [Sources | Dimensions | Method]

Edit `agents/$ARGUMENTS.md` and modify the [sources table | dimensions table | synthesis section].

### Common Modifications

- [Modification 1: e.g., "Add a new data source by adding a row to the Sources table and a search step in the Process"]
- [Modification 2: e.g., "Change score calibration by editing the calibration table at the bottom"]
- [Modification 3: e.g., "Adjust dimension weights by modifying the composite score calculation"]

## Dependencies

- **Reads from:** [what data this agent needs — e.g., "All Wave 1 data files" or "N/A for data agents"]
- **Consumed by:** [what reads this agent's output — e.g., "All Wave 2 evaluators" or "synth-chair"]

Read the full file on GitHub · 105 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. 10d ago First seen · 105 lines · 8 tokens per session scan A 292c9eae3354

Subscribe to this mod's changes

document-agent is a skill published in the GitHub repository golemfoundation/octant-council-builder (3 stars, last pushed 5mo ago), licensed MIT. It adds 8 tokens to every session and 705 once invoked, about $0.0000 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 skills, from other repositories

great_cto

Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.

avelikiy/great_cto · 32 tokens

anti-patterns

Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).

avelikiy/great_cto · 59 tokens

cost-model

Standardized cost-estimation framework for greatcto plans. Forces explicit LLM cost, infra cost, human-supervision time, and the (defensible) human-equivalent comparison. Output format is parsable by the board's /api/cost path — must follow exactly.

avelikiy/great_cto · 59 tokens

migration-ready-schema

Data-model rules that make a schema importable from day one, so the migration-import-engineer is never blocked on missing columns. Every SMB Product-Builder product must let a customer bring their data from an incumbent (ServiceTitan/Toast/Mindbody/Shopify) — that requires provenance (sourceref) and rollback…

avelikiy/great_cto · 133 tokens

stack-baseline

The pinned default technology stack for SMB Product-Builder products. One source of truth so the architect, app-scaffolder, auth-engineer, and senior-dev never re-decide the stack per build — they build ON it. Covers framework, ORM/DB, auth, UI, payments/email/SMS, files, jobs, testing, hosting, and observability…

avelikiy/great_cto · 126 tokens

agent-workflow-playbook

AI Agent Workflow & Skill Architecture Guide — turn expert work into measurable, reusable agent systems. Covers workflow discovery, skill decomposition, harness design, evaluation, human escalation, observability, cost control, and multi-agent orchestration. Includes a measured marketing-delivery case: 15 people × 3–4…

Gingiris-1031/gingiris-skills · 83 tokens