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 skills add flukeatzerocool/infobroker --skill technical-writinggit clone --depth 1 https://github.com/flukeatzerocool/infobrokerWrote 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/skills/flukeatzerocool/infobroker/technical-writing)<a href="https://agentmods.dev/skills/flukeatzerocool/infobroker/technical-writing"><img src="https://agentmods.dev/badge/skills/flukeatzerocool/infobroker/technical-writing/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.
<a href="https://agentmods.dev/skills/flukeatzerocool/infobroker/technical-writing"><img src="https://agentmods.dev/badge/skills/flukeatzerocool/infobroker/technical-writing.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00042 | $0.01131 |
| Opus 5.5 | $0.00017 | $0.00452 |
| Sonnet 5.5 | $0.00008 | $0.00226 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
technical-writing 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Writing
When NOT to Use
- For marketing or persuasive copy.
- When source material is missing and no one can provide authoritative details.
- For git-integrated changelog workflows — use
changelog-before-commitinstead.
Workflow
-
Identify document type and audience. Determine whether the output is an API reference, tutorial, user guide, changelog, or architecture doc. Adjust depth and vocabulary for the reader. When the Infobroker orchestrator invokes this skill as the WRITE step of a workflow shape, the document type is a research report and its structure is the shared skeleton plus the routed shape's block in
skills/infobroker/references/report-template.md. Report conventions take precedence over the API-reference, tutorial, and user-guide templates below. -
Gather source material. Collect code, schemas, existing docs, design documents, and commit history. Identify authoritative sources.
Infobroker Integration: Source material comes from the extract and verify phases of the Infobroker pipeline —
search_webandfetch_page. Usefetch_pagewith Jina Reader for clean Markdown of web sources. -
Design the structure. Create an outline that follows conventions for the document type. API references use a per-endpoint template; tutorials follow step-by-step progression.
-
Write the content. Use clear, direct language. Prefer active voice and short sentences. Include complete, runnable code examples. Define acronyms on first use.
-
Add navigation. Include a table of contents, cross-references, and "Next steps" sections.
-
Review. Verify code examples run, endpoints match the implementation, and no placeholder text remains.
Research Reports (Infobroker workflow shapes)
When this skill runs as the Infobroker WRITE step, write a research report, not generic documentation:
- Use the routed shape. The orchestrator supplies the workflow shape,
audience, and target length. The structure is the shared skeleton in
skills/infobroker/references/report-template.mdplus that shape's block. Emit thereport-manifestblock and record the audience profile (executive / analyst / engineer) in it. - Fill every section. Executive Summary, Methodology & Scope, Key Findings, Assumptions, Analysis of Alternatives, Evidence & Sources, Contradictions, Gaps, Source Register, and Recommendations. Do not drop a section because it is empty — state "none found" or why it does not apply. For a Literature Review, also fill the PRISMA-style identification and screening table with exclusion reasons.
- Preserve evidence binding. Keep the
[S#]marker assigned during verification on every factual claim. Before handing the draft back, perform a redraft check: extract each claim from the draft, confirm the evidence set supports it, and remove or mark unverified any claim it does not support. Do not introduce a claim while drafting. - Calibrate to the reader. Executive audiences lead with the summary and recommendations; technical audiences lead with method and findings. Honor the requested length rather than padding to a fixed size.
- Do not substitute a documentation genre. An API reference or tutorial is the wrong deliverable for a routed research shape.
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.
- 9d ago Changed · +6 lines 55c7baf1a84f
- 16d ago Changed · +30 lines a3177174dae3
- 2mo ago Changed cb7d708a2ff0
- 2mo ago First seen · 83 lines · 42 tokens per session scan A db17010e6a3b
technical-writing is a skill published in the GitHub repository flukeatzerocool/infobroker (1 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 1,131 once invoked, about $0.0002 per session on Opus 5.5. 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.
technical-writing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| technical-writingflukeatzerocool/infobroker | Skill | 1 | 2d ago | MIT | A | 42 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |