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/code-payments/code-android-app/release-notesnpx skills add code-payments/code-android-app --skill release-notesgit clone --depth 1 https://github.com/code-payments/code-android-appWhat 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 | $0.00050 | $0.01049 |
| Opus 5 | $0.00025 | $0.00524 |
| Sonnet 5 | $0.00010 | $0.00210 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
release-notes 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 2d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Notes Generator
Generate polished GitHub release notes for the code-android-app repository.
Pre-flight context
- Latest tag: !
git describe --tags --match 'fcash/*' --abbrev=0 HEAD 2>/dev/null || echo "no tags found" - All recent tags: !
git tag --sort=-creatordate | head -10
Input
Parse the two refs from $ARGUMENTS. Each ref can be a tag, a commit SHA, a commit number (Nth commit in repo history), or HEAD:
/release-notes fcash/2026.4.10 fcash/2026.4.11/release-notes fcash/2026.4.9 HEAD/release-notes a3f2417 HEAD/release-notes 3599 HEAD(from the 3599th commit to HEAD)
If only one ref is provided, use it as <from> and default <to> to HEAD.
If no refs are provided, use the pre-flight latest tag as <from> and HEAD as <to>.
Steps
1. Run the changelog script
bash scripts/changelog.sh <from_tag> <to_tag>
Display the raw output for the user to see.
2. Rewrite into release notes
Use the Agent tool with model: "haiku". Pass the raw changelog output with this prompt:
Given these git commits (conventional commit format), write user-facing release notes.
Rules:
- Group under: Features, Bug Fixes, Improvements, Dependencies (omit empty sections)
- Write for end users — no jargon, file names, or internals
- One short sentence per item
- Group related commits into a single bullet when they address the same area
- Use scope as context but write in plain language; keep scope in bold prefix when it adds clarity
- ALWAYS include bug fixes — only drop pure refactors, CI pipeline changes, and release/manifest bookkeeping
- Feature bullets start with a lowercase verb (e.g., "add", "support", "enable")
- Bug fix bullets start with "Fixed" (capitalized)
- Dependencies section: list each dependency bump as
Name X.Y.Z → A.B.C(use the human-readable library name, not the Maven coordinate). Include targetSdkVersion and Gradle wrapper bumps in this section too.- Use 2-space indent before each bullet (
-)- Do NOT include commit hashes
- If no user-facing changes, output: Bug fixes and performance improvements.
- Output ONLY the section markdown, no title or fences
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.
- 2d ago First seen · 102 lines · 50 tokens per session scan A 89a8cdc0f89d
release-notes is a skill published in the GitHub repository code-payments/code-android-app (23 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 1,049 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 2026-08-30.
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…