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/jircdev/crew-plugin/writingnpx skills add jircdev/crew-plugin --skill writinggit clone --depth 1 https://github.com/jircdev/crew-pluginWhat 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 | $0.00114 | $0.01286 |
| Opus 5 | $0.00057 | $0.00643 |
| Sonnet 5 | $0.00023 | $0.00257 |
| Haiku 4.5 | $0.00011 | $0.00129 |
Grade A, and why
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 yesterday.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing — the communication craft
Formerly the communications-strategist role; now a horizontal craft any role loads when it writes. The domain truth belongs to the owning role (the technical decision to system-architect, viability to commercial-strategist, the requirement to functional-analyst, the product truth to product-strategist); this skill governs how that truth lands.
Method
- Internalize objective and audience. What should they think, feel, or do afterward — and who exactly are they? A piece without a declared objective and audience is not ready to be written.
- Pull the WHAT from its owner. Read the project docs or consult the owning role; never invent or alter domain facts to make the narrative flow.
- Fix the idea-force: the single thing the audience must remember.
- Choose the impact principle that fits — golden circle (why → how → what), storytelling, framing, proof points, exponential framing — because the objective calls for it, never as decoration. State why.
- Design the arc: hook → development → climax → close, beat by beat; for each beat, the message, the visual support required (specify, don't design), the emotional intent.
- Write in the structure proper to the format. The format follows the objective, not a fixed template.
- Close with the call to action or the idea that stays.
- If spoken, add delivery notes: pacing, pauses, emphasis, where energy rises and falls.
- Hand off visual support as a per-beat specification to
ux-architect(owner of the visual system); they design the slides or assets.
Craft rules
- Segmentation: the same idea-force adapts to different audiences and formats without losing coherence — one project can yield a team induction and an external webinar the same week; they are different pieces.
- Register and tone adapt to channel and audience; jargon the audience cannot decode gets glossed or cut.
- Message before context: the why never arrives after the how. Burying the message under background is the most common failure.
- Length sized to the decision, not to the template.
- Senior judgment, not transcription: reorganizing the source material without adding communicational judgment is the anti-pattern this craft exists to prevent.
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.
- yesterday First seen · 63 lines · 114 tokens per session scan A ad7dc28ae477
writing is a skill published in the GitHub repository jircdev/crew-plugin (2 stars, last pushed 12d ago), licensed MIT. It adds 114 tokens to every session and 1,286 once invoked, about $0.0006 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…