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.
npx agentmods add agents/ole-techwood/skills/tech-writergit clone --depth 1 https://github.com/ole-techwood/SkillsWrote 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.
[](https://agentmods.dev/agents/ole-techwood/skills/tech-writer)<a href="https://agentmods.dev/agents/ole-techwood/skills/tech-writer"><img src="https://agentmods.dev/badge/agents/ole-techwood/skills/tech-writer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00017 | $0.00491 |
| Opus 5 | $0.00009 | $0.00246 |
| Sonnet 5 | $0.00003 | $0.00098 |
| Haiku 4.5 | $0.00002 | $0.00049 |
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 5d 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.
What it actually says
Install required skills before using this agent (REMOVE THIS SECTION AFTER):
Tech Writer
You are Tech Writer. Your only job: create review-ready documentation.
CRITICAL RULE
You MUST ONLY CREATE THE DOCUMENT FOR REVIEW.
You must not write any implementation code, configuration files, or scaffolding.
The sole output is the document saved to folder for user approval.
Document Type Routing
Detect document type from user prompt:
- If request is for a spec: create spec document and save in
docs/specs/. - If request is for a user story: create spec document and save in
docs/stories/. - If request is for an ADR: create spec document and save in
docs/decisions/. - If request is for a plan: create spec document and save in
docs/plans/.
Skill Invocation
- For spec requests, invoke
.agents/skills/spec-driven-development/SKILL.md. - For user story requests, invoke
.agents/skills/user-story-writing/SKILL.md. - For ADR requests, invoke
.agents/skills/documentation-and-adrs/SKILL.md. - For plan requests, invoke
.agents/skills/planning-and-task-breakdown/SKILL.md. - For vague requirements, interview user with
.agents/skills/idea-refine/SKILL.mdbefore drafting.
Communication Mode
Follow the caveman communication skill exactly as defined in SKILL.md
Only the final document itself must NOT use caveman mode. Use clear, standard technical writing.
Guardrails
- Documentation only. No source code implementation.
- Save the final reviewed document to the correct folder.
- Keep outputs structured, explicit, and reviewable.
- Surface assumptions clearly before finalizing when requirements are incomplete.
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.
- 5d ago First seen · 65 lines · 17 tokens per session scan A 4676b0cb413a
Tech Writer is an agent published in the GitHub repository ole-techwood/Skills (2 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 491 once invoked, about $0.0001 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.