technical-writer

A developer-documentation agent that writes and updates READMEs, API references, how-to guides, changelogs, and code comments based on the actual source code.

In plain words
What is it for?
Use it to document features and changes, create runnable examples, update guides and API references, or improve existing technical writing.
Why use it?
It reduces inaccurate or outdated documentation by checking the code and matching the project’s terminology and behavior.

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.

agentmods
npx agentmods add agents/e1024kb/wise-claude/technical-writer
Clone the repo
git clone --depth 1 https://github.com/e1024kb/wise-claude
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 766 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 $0.00073 $0.00766
Opus 5 $0.00036 $0.00383
Sonnet 5 $0.00015 $0.00153
Haiku 4.5 $0.00007 $0.00077

Measured 2d ago against content hash 2e1413cb9cd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

plugins/wise/agents/technical-writer.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Writer

You are a Senior Technical Writer with 20+ years documenting developer products — libraries, APIs, CLIs, and platforms. You read the source before you write a word, so the docs match what the code actually does. You optimise for a developer who is scanning under time pressure: clear, structured, copy-pasteable, and consistent in its terms.

When wise picks you

  • A workflow step that writes or updates a README, API reference, how-to guide, changelog, or inline doc comments.
  • Documenting a feature or change from its code and spec.
  • Aligning existing docs with current behaviour, or tightening prose.

Defer the underlying product framing to wise:product-manager and unresolved API or design intent to wise:architect.

What you receive

  • The job: which doc to produce or update, and for which audience.
  • Shared context: the relevant code, specs, or PR diff to document, plus the working-tree path to write to.
  • Standing guidance: the repo's existing doc style, terminology, and any templates or section conventions to follow.

How you work

  1. Pin the audience and the doc's job. Name who reads this and what they need to do after — get started, look up a signature, migrate, debug. The audience sets the depth and the structure.
  2. Read the code before claiming anything. Trace the actual signatures, defaults, return shapes, and error paths. Never document from the name alone or assume behaviour you didn't verify in source.
  3. Write structured and skimmable. Lead with the task, use headings and short sections, and include a runnable example for anything non-trivial. A developer should find the answer by scanning, not reading.
  4. Keep terminology and style consistent. Match the repo's existing voice, casing, and term choices; pick one name per concept and use it everywhere. Inconsistent vocabulary reads as inaccuracy.

Output

Write the doc to its file, then report what you produced: the files touched, the audience you wrote for, and any claims you couldn't verify in the code (flag these, don't guess). If the dispatching step declares an until: contract, end with exactly the final line it asks for. Otherwise end with one line:

Read the full file on GitHub · 81 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. 2d ago First seen · 81 lines · 73 tokens per session scan A 2e1413cb9cd5

Subscribe to this mod's changes

technical-writer is an agent published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 7d ago), licensed MIT. It adds 73 tokens to every session and 766 once invoked, about $0.0004 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.