technical-writer

technical-writer is a skill for Codex from jscraik/Agent-Skills. It costs 63 tokens per session (1,587 once invoked), scanned A, original, Apache-2.0.

A documentation review and rewriting guide for READMEs, runbooks, code and configuration guides, and other public-facing technical material. It checks claims against evidence from the repository and its workflows.

In plain words
What is it for?
Use it to audit or rewrite technical docs, correct unsupported claims, document configuration and package behavior, and check reader-visible documentation access.
Why use it?
It helps prevent documentation from promising behavior that the code, scripts, or support process do not provide. It also clarifies which file is responsible for generated or published documentation.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to audit or rewrite technical docs, correct unsupported claims, document configuration and package behavior, and check reader-visible documentation access.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jscraik/agent-skills/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 jscraik/Agent-Skills --skill technical-writer
Clone the repo
git clone --depth 1 https://github.com/jscraik/Agent-Skills

Made for: 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/jscraik/agent-skills/technical-writer/github.svg)](https://agentmods.dev/skills/jscraik/agent-skills/technical-writer)
Your own site
<a href="https://agentmods.dev/skills/jscraik/agent-skills/technical-writer"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/technical-writer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for technical-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/jscraik/agent-skills/technical-writer"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/technical-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,587 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 $0.00063 $0.01587
Opus 5 $0.00032 $0.00794
Sonnet 5 $0.00013 $0.00317
Haiku 4.5 $0.00006 $0.00159

Measured 8d ago against content hash cabbdd3af110, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 8d 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/agent-ops/technical-writer/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Writer

When To Use

  • README, runbook, code-doc, template, config-doc, or trust-surface docs need audit or rewrite.
  • Skill package evidence or runtime-boundary docs need proof-backed explanation.
  • Claims need checks against scripts, commands, workflows, tests, repo structure, support paths, or governance docs.
  • Generated, mirrored, registry, or publication docs need canonical ownership and reader-visible validation.
  • Talks, articles, DevRel content, service content, visual docs, and short-form writing need evidence-backed technical shaping.

Inputs

Doc target, audience, reader job, writing mode, truth files, validation commands, glossary or ubiquitous-language surfaces, and brand/governance constraints.

Outputs

For audits and broad rewrites, return findings, claim/evidence map, ownership decisions, validation, unknowns, and handoff needs. For narrow corrections, return the corrected text or patch plus exact evidence. For editorial judgment, return verdict, central risk, revision direction, and a rewrite only when requested. Return no_justified_edit when documentation is not the safe owning surface.

Execution Boundaries

Inspect applicable instructions and preserve the current worktree before drafting. Edit only the canonical documentation owner. Treat generators, runtime or mirrored copies, registries, publication surfaces, user configuration, and external systems as separate lanes. Do not invent commands, paths, versions, access, platform behavior, or readiness claims. Do not change runtime behavior, dependencies, CI, release state, trackers, projections, or publication state without the owning workflow and approval.

Discovery interview

Inspect known, read-only surfaces without delay. When the editable boundary is materially unknown, ask one plain-language question before edits: ask which documentation surface to inspect, identify the canonical source path or editable owner, and block edits until that surface is chosen. For a staged package, ask for its source path or editable scope rather than guessing. Ask one round at a time, explain why this matters, and avoid dumping the full interview plan at once.

Read the full file on GitHub · 79 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 79 lines · 63 tokens per session scan A cabbdd3af110

Subscribe to this mod's changes

technical-writer is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,587 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 2026-09-03.