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/felipecabargas/gambit/write-release-notesnpx skills add felipecabargas/gambit --skill write-release-notesgit clone --depth 1 https://github.com/felipecabargas/gambitWhat 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 | $0.00101 | $0.02756 |
| Opus 5 | $0.00051 | $0.01378 |
| Sonnet 5 | $0.00020 | $0.00551 |
| Haiku 4.5 | $0.00010 | $0.00276 |
Grade A, and why
write-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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Notes Writer
When to Use
Use this skill when you need to turn internal sprint or release output into clear, customer-facing communication. It adds the most value when:
- After every sprint or release — converting raw ticket output into polished release notes is time-consuming and error-prone when done manually. This skill does the filtering, rewriting, and grouping in one pass.
- When publishing a changelog — a public changelog requires a consistent voice, accurate grouping (New vs. Improved vs. Fixed), and zero internal jargon. This skill enforces all three.
- When preparing a product announcement — release announcements need a highlights section that leads with customer impact, not a flat list of tickets. This skill surfaces the most impactful items and writes the opening narrative automatically.
Input Format
The skill accepts several input forms. The richer the input, the better the filtering and rewriting.
Sprint review output from sprint-review:
Path: ./sprint-review-2026-05-05.md
Pasted ticket list (with or without descriptions):
- PROJ-1042: Refactor auth middleware to use JWT
- PROJ-1043: Add bulk CSV export to reporting page
- PROJ-1044: Fix crash on mobile when attachment > 5MB
- PROJ-1045: Upgrade React to 18.3
- PROJ-1046: Users can now set a custom notification schedule
PR list from a release branch:
PR #312: feat: add CSV export to reports
PR #314: fix: mobile crash on large attachment upload
PR #315: chore: upgrade React 18.3
PR #316: refactor: auth middleware JWT migration
Optionally, channel context to set the tone:
Channel: in-app tooltip / email announcement / public changelog / marketing landing page
If no channel is specified, the skill defaults to public changelog tone and notes the assumption.
Filtering Rules
The first and most important step is filtering. Only customer-visible work belongs in release notes. Everything else is noise that dilutes the signal and wastes readers' attention.
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 · 241 lines · 101 tokens per session scan A ebb70802b10d
write-release-notes is a skill published in the GitHub repository felipecabargas/gambit (2 stars, last pushed 3mo ago), licensed MIT. It adds 101 tokens to every session and 2,756 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 2026-08-31.
Other skills, from other repositories
antigravity
Run the Antigravity CLI (Gemini) as a collaborating AI inside Claude Code, with intelligent model routing across the software development lifecycle. Claude is the conductor/orchestrator — requirements, architecture, the hard 20%, verification, and review — and routes deterministic, high-volume work (scaffolding…
migrate-to-antigravity
Move an existing Claude Code setup onto the Antigravity CLI (agy) — user skills, CLAUDE.md, auto-memory, MCP servers, installed plugins, permissions and trusted workspaces. Use when the user says "migrate to Antigravity", "move my Claude Code config to agy", "bring my skills/memory/MCP over", "set up agy like my…
bump-version
Bump the Logic-Lens version across all six metadata locations at once (package.json, the four plugin manifests, and the README badge), then validate. Use when cutting a release or when npm run validate reports a version mismatch.
deploy-pipeline-runbook
Use when a release spans multiple systems or vendors, order of operations matters with rollback planned up front, or a failed step in one system could corrupt state in a downstream system.
vr-planner
Plans how to verify changes to an os-autoinst-distri-opensuse (OSADO) checkout. Use this skill when the user asks "how do I test my change", "what verification run (VR) should I do", "which openQA job should I clone", or "what's affected by my edit". Determines required unit tests, affected test modules, YAML…
openqa-log-analyzer
A specialized skill for analyzing openQA logs — triage failures, measure command timing, detect infrastructure lag, extract command output, and compare runs across multiple log files.