technical-writer

technical-writer is a skill for Claude Code, Codex from henryh/AI-SpecDoc. It costs 61 tokens per session (675 once invoked), scanned A, original, MIT.

A documentation workflow for keeping project documentation accurate after development work and recording important decisions as ADRs, or architecture decision records.

In plain words
What is it for?
Finding the right documentation, summarizing completed work, checking task records, and adding ADR entries when the project requires them.
Why use it?
It reduces stale task statuses, missing documentation, and lost reasoning behind changes to code, testing, or development processes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Finding the right documentation, summarizing completed work, checking task records, and adding ADR entries when the project requires them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/henryh/ai-specdoc/technical-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.

Any agent
npx skills add henryh/AI-SpecDoc --skill technical-writer
Clone the repo
git clone --depth 1 https://github.com/henryh/AI-SpecDoc

Made for: Claude Code, Codex.

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 technical-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/henryh/ai-specdoc/technical-writer.svg)](https://agentmods.dev/skills/henryh/ai-specdoc/technical-writer)
Your own site
<a href="https://agentmods.dev/skills/henryh/ai-specdoc/technical-writer"><img src="https://agentmods.dev/badge/skills/henryh/ai-specdoc/technical-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 675 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 $0.00061 $0.00675
Opus 5 $0.00030 $0.00338
Sonnet 5 $0.00012 $0.00135
Haiku 4.5 $0.00006 $0.00068

Measured 7d ago against content hash 6ad941aeb549, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

technical-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 7d 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/technical-writer/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Writer

Overview

Update project documentation as part of task completion and capture decisions in ADRs when the project requires ADRs and process, testing, or development approaches change.

Workflow

  1. Identify doc targets via docs/index.md.
  2. Summarize task outcomes and update the relevant docs with concise, testable statements.
  3. If a decision was made or a workflow/testing approach changed, add a dated ADR entry in docs/adr.md only when the project requires ADRs.
  4. Verify task statuses: ensure no leftovers, duplicates, or stale fragments between Active and Done; correct any inconsistencies found.
  5. If review raised questions or uncovered gaps, note them in the relevant doc (or ADR) and align on next steps.
  6. Keep updates minimal and consistent with existing tone and structure.

Mandatory Documentation Triggers

  • If the user explicitly requests documentation changes during a task, treat them as required for TW: apply the doc updates as part of the documentation phase before closing the task.

ADR Guidance

  • Add ADRs only if the project requires ADRs.
  • If ADRs are required, add them for: decisions made during implementation or review, changes to testing strategy, or development workflow updates.
  • Keep ADRs concise: context, decision, consequences, date.
  • One ADR entry must capture exactly one decision. If there are multiple decisions, split them into separate ADR entries.
  • Append new ADR entries to docs/adr.md; do not overwrite prior decisions.

Output Checklist

  1. Docs updated only where scope changed.
  2. ADR added when decisions or workflow/testing changes occurred and the project requires ADRs.
  3. Task lists checked for clean statuses (no duplicates or leftovers between Active and Done).
  4. Review questions captured and reconciled with documentation.

Output Discipline

  • Find first, then read the minimum necessary.
  • Do not read large files unless required.
  • Avoid large quotes; return a concise extract instead of raw text.
  • Output should be a compressed container, not a dialogue.

Read the full file on GitHub · 56 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. 7d ago First seen · 56 lines · 61 tokens per session scan A 6ad941aeb549

Subscribe to this mod's changes

technical-writer is a skill published in the GitHub repository henryh/AI-SpecDoc (2 stars, last pushed 6mo ago), licensed MIT. It adds 61 tokens to every session and 675 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens