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 Vimalk0703/shipworthy --skill writing-skillsgit clone --depth 1 https://github.com/Vimalk0703/shipworthyWrote 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/vimalk0703/shipworthy/writing-skills)<a href="https://agentmods.dev/skills/vimalk0703/shipworthy/writing-skills"><img src="https://agentmods.dev/badge/skills/vimalk0703/shipworthy/writing-skills/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/vimalk0703/shipworthy/writing-skills"><img src="https://agentmods.dev/badge/skills/vimalk0703/shipworthy/writing-skills.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 | $0.00056 | $0.04957 |
| Opus 5 | $0.00028 | $0.02478 |
| Sonnet 5 | $0.00011 | $0.00991 |
| Haiku 4.5 | $0.00006 | $0.00496 |
Grade A, and why
writing-skills 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 10d 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Skills
This is the meta-skill: the skill for writing skills. It treats skill authorship with the same rigor as software engineering — because skills ARE production code. They run on every session, shape every output, and compound in effect over time. A sloppy skill causes more damage than a sloppy function because it corrupts behavior across every future interaction.
1. Skills Are Tests for Behavior
Just like code tests verify that software behaves correctly, skills verify that the AI follows correct processes. A test asserts "given input X, the output must be Y." A skill asserts "given situation X, the AI must behave like Y."
This is not a metaphor. Skills are literally executable specifications for AI behavior. They are loaded into context, parsed for rules, and enforced during generation. If a skill is vague, the AI will interpret it loosely — the same way a developer interprets a vague test as "anything goes." If a skill is specific, the AI will follow it precisely — the same way a developer follows a well-written test that leaves no room for misinterpretation.
The consequences of treating skills casually are severe:
- Untested behavior drifts. Without a skill, the AI will handle the same situation differently across sessions. One session it adds error handling; the next it does not. One session it writes tests first; the next it writes code first and "plans to add tests later."
- Rationalizations fill the vacuum. When there is no explicit rule, the AI will rationalize whatever is most convenient. "The user seems to want speed, so I'll skip the security check." Skills close this gap by making the expected behavior explicit.
- Compounding errors. A missed skill in session 1 produces code that session 2 builds on top of. By session 5, the architectural debt is load-bearing and expensive to fix.
Write skills the same way you write tests: identify the failure first, then write the fix. Never write a skill because "it seems like a good idea." Write it because you have evidence of a specific failure that the skill will 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.
- 10d ago First seen · 369 lines · 56 tokens per session scan A 23f37d2d0097
writing-skills is a skill published in the GitHub repository Vimalk0703/shipworthy (7 stars, last pushed 5mo ago), licensed MIT. It adds 56 tokens to every session and 4,957 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 2026-08-31.
Other skills, from other repositories
hedgehog-planning-intake
Use on any core for first-run planning intake — Phase 0 runs the vendored BMAD-METHOD planning shelf, shared by every core, and Phase 1 (mining 04-prd.md into intent records plus the Add-ons/sync-and-remote-entities decision) is full-stack-app's and pwa-app's shared procedure — identical mechanics, a different…
bmad-product-brief
Create, update, or validate a product brief. Use when the user wants help producing, editing, or validating a brief.
bmad-deep-recon
Decision-grade research, three ways: draft a deep-research prompt for the user to run in their own tool (ChatGPT, Gemini, Grok, Perplexity, …), process a finished research report — file it, distill a succinct cited summary with metadata that downstream skills consume without reprocessing — or run the research here…
hedgehog
Use when the user writes the word "Hedgehog" anywhere in a request, or has agreed to install the Hedgehog build discipline in a project that does not have it yet. Hedgehog builds prose as well as code — articles, essays, blog posts, tweets, threads, newsletters, announcements, and marketing or product copy of any…
conventional-commits
Use when uncommitted changes need to be split into atomic, conventional commits ordered for review. Triggers on "commit this", "make commits", "clean up commits", "commit the changes". In Hedgehog, each Loop step is already meant to be its own commit — this skill matters most when a Correction Protocol fast-forward…
hedgehog-contributing
Use when the user wants to contribute a fix or roadmap item back to the Hedgehog project itself (skyf0xx/hedgehog) rather than their own project. Triggers on "let's fix that in Hedgehog", "I want to contribute", "let's pick up a roadmap item", or when tweaker offers this at the end of a build and the user says yes.…