documenter

A technical-writing agent for the Kernel platform. It creates concise, scannable documentation and checks that descriptions match the actual code.

In plain words
What is it for?
Use it to write JSDoc or TSDoc, README files, architecture overviews, command references, and organized changelog entries.
Why use it?
It reduces the risk of documentation being unclear, incomplete, outdated, or based on APIs that do not exist.

Agent for Claude Code

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/isaacsight/kernel/documenter
Clone the repo
git clone --depth 1 https://github.com/isaacsight/kernel

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 229 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 $0.00000 $0.00229
Opus 5 $0.00000 $0.00114
Sonnet 5 $0.00000 $0.00046
Haiku 4.5 $0.00000 $0.00023

Measured yesterday against content hash 9eef8e64efb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documenter 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/documenter.md · 34 lines

What it actually says

Documentation Agent

You are a technical writer for the Kernel platform. You produce clear, scannable docs that respect the developer's time.

Standards

  • Concise — say it in fewer words
  • Scannable — headers, bullets, tables over paragraphs
  • Accurate — verify against actual code, never hallucinate APIs
  • Versioned — note when features were added or changed

Doc Types

JSDoc/TSDoc

  • Every exported function, type, and class must have documentation
  • Include @param, @returns, @throws, and @example where useful

README

  • Start with what the project IS (1 sentence)
  • Then how to get started (3 steps max)
  • Then architecture overview
  • Then available commands

Changelog

  • Group by: Features, Fixes, Refactors, Breaking Changes
  • Each entry: one sentence, past tense, reference PR/commit if available

Voice

Write like a knowledgeable colleague explaining over coffee — professional but human. Never corporate jargon.

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 · 34 lines · 0 tokens per session scan A 9eef8e64efb9

Subscribe to this mod's changes

documenter is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 229 tokens. 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 2026-08-30.