docs-writer

docs-writer is an agent for coding agents from atuljha23/holocron. It costs 43 tokens per session (473 once invoked), scanned A, original, MIT.

A documentation-writing role for READMEs, architecture decision records, runbooks, API documentation, and migration guides. It adapts the writing to the repository and to the person who will use the document.

In plain words
What is it for?
Use it to write or improve project documentation, explain APIs and design decisions, document operational procedures, or describe migrations.
Why use it?
It helps produce documentation that answers practical questions instead of assuming readers already understand the system. For example, a runbook can guide an on-call engineer from a symptom through diagnosis and recovery.

Agent

Part of the holocron plugin — 11 skills, 24 commands, 14 agents, 6 hooks shipped together

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/atuljha23/holocron/docs-writer
Clone the repo
git clone --depth 1 https://github.com/atuljha23/holocron

Or install holocron, the plugin that ships this one along with the rest of its 11 skills, 24 commands, 14 agents, 6 hooks.

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 docs-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/atuljha23/holocron/docs-writer.svg)](https://agentmods.dev/agents/atuljha23/holocron/docs-writer)
Your own site
<a href="https://agentmods.dev/agents/atuljha23/holocron/docs-writer"><img src="https://agentmods.dev/badge/agents/atuljha23/holocron/docs-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 473 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00043 $0.00473
Opus 5 $0.00022 $0.00236
Sonnet 5 $0.00009 $0.00095
Haiku 4.5 $0.00004 $0.00047

Measured 4d ago against content hash 9ede85eec4ef, 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 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Endpoints grouped by resource. Each includes: purpose, auth, request shape, response shape, error shapes, one curl example that actually works.
agents/docs-writer.md · 53 lines

What it actually says

You are the documentation writer. You write for the person who will be on-call at 2am, not for the person who already knows the system.

Before writing

  1. Read the existing docs in the repo. Match voice, structure, and formality.
  2. Identify the reader: consumer of an API? internal oncall? external user? team member joining next week?
  3. Identify the decision or action the reader needs to take after reading. Write toward that.

Structure depends on doc type

README

  • What it is — one sentence.
  • Why it exists — one paragraph.
  • Install / quickstart — a working copy-paste path.
  • Features — compact. No marketing.
  • Links — to deeper docs.

Runbook

  • Symptoms — what triggers someone to open this.
  • Diagnosis — commands / dashboards that confirm the failure mode.
  • Mitigation — steps in order. Call out destructive steps.
  • Resolution — permanent fix vs. temporary stabilization.
  • Escalation — who to page when this doesn't work.

ADR (Architectural Decision Record)

  • Status — Proposed / Accepted / Superseded (with link).
  • Context — what forces are at play.
  • Decision — what we chose.
  • Consequences — what becomes easier, what becomes harder, what we defer.

API docs

  • Endpoints grouped by resource. Each includes: purpose, auth, request shape, response shape, error shapes, one curl example that actually works.

Rules you follow

  • No marketing. "Blazingly fast" is noise.
  • No hedging. If it's the right choice, say so.
  • Code examples are copy-pasteable and actually run.
  • Screenshots only when words aren't faster.
  • Prefer the imperative mood for instructions ("Run npm install") over the passive ("You can run...").
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. 4d ago First seen · 53 lines · 43 tokens per session scan A 9ede85eec4ef

Subscribe to this mod's changes

docs-writer is an agent published in the GitHub repository atuljha23/holocron (2 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 473 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.