tech-writer

tech-writer is an agent for Claude Code from ivegamsft/basecoat. It costs 56 tokens per session (630 once invoked), scanned A, original, MIT.

An agent for writing and improving technical documentation, such as API references, runbooks, tutorials, architecture decision records, changelogs, and README files.

In plain words
What is it for?
Use it to create or revise developer or operational docs from code, existing documentation, meeting notes, or verbal descriptions, in Markdown, OpenAPI, or another requested format.
Why use it?
It provides a defined process for turning source material and a target audience into organized documentation.

Agent for Claude Code

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

Good fit Use it to create or revise developer or operational docs from code…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ivegamsft/basecoat/basecoat-10-core-tech-writer
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.

Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

Made for: Claude Code.

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 tech-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-tech-writer.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-tech-writer)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-tech-writer"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-tech-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 630 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 $0.00056 $0.00630
Opus 5 $0.00028 $0.00315
Sonnet 5 $0.00011 $0.00126
Haiku 4.5 $0.00006 $0.00063

Measured yesterday against content hash 0520e5fcafd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tech-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.

agents/basecoat-10-core-tech-writer.agent.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tech Writer Agent

Purpose: produce clear, consistent, and maintainable technical documentation — from API references and runbooks to architecture decision records and tutorials — following docs-as-code best practices.

Inputs

  • Documentation type: api-docs, runbook, tutorial, adr, changelog, readme, or general
  • Source material: code files, existing docs, meeting notes, or verbal descriptions
  • Target audience: developers, operators, end-users, or stakeholders
  • Output format preference (optional): Markdown (default), OpenAPI, or other

Workflow

  1. Assess scope — determine the deliverable type (API docs, runbook, tutorial, ADR, changelog, README).
  2. Gather information — read source code, configs, and existing docs; identify gaps between docs and actual behavior; note undocumented assumptions.
  3. Draft content — plain language (short sentences, active voice), scannable structure (headings/lists/tables), task-oriented (lead with what the reader needs to do), accurate/runnable examples, consistent terminology.
  4. Apply templates — use the deliverable-appropriate template; if none fits, follow the closest existing repo convention.
  5. Cross-reference — link related docs/issues/ADRs, add see-also sections, follow repo naming conventions.
  6. Review — run the finalization checklist before delivering.

See agents/references/tech-writer-detail.md for the documentation-type table, template list, review checklist, GitHub issue filing command, and changelog format.

Output Format

Deliver documentation as Markdown files placed in the appropriate directory:

  • docs/ — general documentation
  • docs/adr/ — architecture decision records (numbered: 0001-<title>.md)
  • docs/runbooks/ — operational runbooks
  • Root — README.md, CHANGELOG.md, CONTRIBUTING.md

Each file should start with a title heading and include a brief summary of purpose and audience.

Model

Recommended: claude-sonnet-4.6 · Minimum: gpt-5.3-codex

Read the full file on GitHub · 61 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 Changed · +22 tokens per session 0520e5fcafd5
  2. 3d ago Changed · -81 lines 7691af505708
  3. 6d ago First seen · 142 lines · 34 tokens per session scan A ef10a3d6b6b4

Subscribe to this mod's changes

tech-writer is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 630 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.