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 tony/skills --skill pr-releasegit clone --depth 1 https://github.com/tony/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/skills/tony/skills/pr-release)<a href="https://agentmods.dev/skills/tony/skills/pr-release"><img src="https://agentmods.dev/badge/skills/tony/skills/pr-release/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/tony/skills/pr-release"><img src="https://agentmods.dev/badge/skills/tony/skills/pr-release.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 | $0.00028 | $0.00915 |
| Opus 5.5 | $0.00011 | $0.00366 |
| Sonnet 5.5 | $0.00006 | $0.00183 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
pr-release 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Release (tier 3)
Derive a one-page announcement from the public case study, and only from it. The public case study is the sanitization firewall: this skill introduces no figure that is not already in it and re-derives nothing from the interim package.
Read ../../references/interim-format.md first, only § Where runs live,
§ Locating an existing run, and § Rendering a report; there is no
completeness gate here. The scanner reads the run's README.md only for
the names the sweep denies. Defer these until the firewall (the public
case study) is located:
../../references/provenance.md../../references/audiences.md: the tier-3 contract and the firewall sweep.
User arguments: $ARGUMENTS
Procedure
1. Locate the run
The $ARGUMENTS path if given, else per interim-format.md §
Locating an existing run; for a named workflow, the first line of
runs --workflow <slug>.
2. Locate and verify the firewall
Check for <run>/reports/case-study-public.md. If it is missing,
ask via AskUserQuestion whether to write it now (read
../case-study-public/SKILL.md and follow it) or stop; never draft
the release straight from the interim package. Without a question
tool, halt with the second stopped-run example in interim-format.md.
If present, run ../../scripts/business.py fresh <run> (absolute path):
a case-study-public.md line means the case study is unstamped or its
run inputs changed, so regenerate it with
/business:case-study-public before going on. Then run the firewall
sweep from audiences.md; a sweep failure routes back to the public
case study, never into hand-patching here.
3. Compose one page
From the public case study only:
- Headline result: the case study's headline, with its tag and range.
- Supporting numbers: two or three, each with its denominator and window length, exactly as they appear in the case study.
- Quote placeholder: clearly marked as a placeholder, with attribution left blank for the user to fill.
- Limitations one-liner: a single candid sentence distilled from the case study's limitations section.
What ships with it
1 file 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.
- 5d ago Changed · +12 lines 246297df26c2
- 8d ago Changed · -4 lines · -2 tokens per session 466254af731a
- 16d ago Changed · -5 lines 546001f52921
- 1mo ago First seen · 88 lines · 30 tokens per session scan A 268e48db037a
pr-release is a skill published in the GitHub repository tony/skills (0 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 915 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…