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 skills/tokenbender/agent-guides/technical-writing-workflownpx skills add tokenbender/agent-guides --skill technical-writing-workflowgit clone --depth 1 https://github.com/tokenbender/agent-guidesWhat 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 | $0.00097 | $0.01113 |
| Opus 5 | $0.00048 | $0.00557 |
| Sonnet 5 | $0.00019 | $0.00223 |
| Haiku 4.5 | $0.00010 | $0.00111 |
Grade A, and why
technical-writing-workflow 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 3d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical writing workflow
Use this skill when the user asks to write, rewrite, improve, audit, explain, teach, document, or publish technical material. Treat it as a workflow with checks, not as a prose vibe.
Core rule
Open the subject up without making it shallow.
Every important explanation must name:
- the object or behavior being described
- the method, mechanism, or actor that changes it
- the evidence that supports the claim
- the boundary the claim is allowed to cover
Serial before parallel
Serialize meaning. Parallelize collection.
Do these serially before drafting:
- Define the reader and use case.
- Define scope and exclusions.
- Build the ontology table.
- Decide the argument order.
- Write chapter or section contracts.
- Resolve source contradictions.
Then parallelize:
- source packets
- paper cards
- glossary entries
- examples
- diagrams
- exercises
- tables
- reference checks
- local fact checks
- counterexamples and failure modes
Return to serial work for:
- synthesis
- final claim strength
- voice and terminology
- cross-references
- final layout or render inspection
The workflow
1. Intake
Write a short brief before drafting:
- audience
- task the reader should perform after reading
- source surface
- deliverable format
- deadline or depth target
- claim-risk level
If any of these are unknown, make a conservative assumption and state it briefly.
2. Source audit
Separate sources into evidence classes:
- primary paper or official documentation
- benchmark or measurement artifact
- code or reproducibility artifact
- technical blog or explainer
- social post or pointer
- local note or capture
Do not let a pointer carry a claim that belongs to a paper, code artifact, or measurement.
3. Ontology table
For each major topic, create this table before drafting:
Topic:
Object:
Method:
Resource or behavior changed:
Evidence:
Boundary:
Common beginner mistake:
Best example:
This table is the backbone. If it is confused, the prose will be confused.
What ships with it
5 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.
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.
- 3d ago First seen · 188 lines · 97 tokens per session scan A 3aef810accf3
technical-writing-workflow is a skill published in the GitHub repository tokenbender/agent-guides (368 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 97 tokens to every session and 1,113 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…