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/byx-darwin/gitflow-cli/gf-releasenpx skills add byx-darwin/gitflow-cli --skill gf-releasegit clone --depth 1 https://github.com/byx-darwin/gitflow-cliWhat 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 | $0.00058 | $0.01559 |
| Opus 5 | $0.00029 | $0.00779 |
| Sonnet 5 | $0.00012 | $0.00312 |
| Haiku 4.5 | $0.00006 | $0.00156 |
Grade A, and why
gf-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 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gf-release
CRUD wrapper for gf release. Manages GitHub/GitLab/GitCode releases — metadata only; tag must exist first. Delete is irreversible.
CLI Requirement
MUST use gf CLI, NOT gh CLI.
| CLI | Scope | Platform Support |
|---|---|---|
gf |
This project | GitHub + GitLab + GitCode |
gh |
GitHub only | GitHub only |
Why: gf is the unified CLI for this project. Using gh breaks GitLab/GitCode compatibility.
Preconditions
gfinstalled:command -v gfgfauthenticated:gf auth status
When to Use
| English | 中文 | Context |
|---|---|---|
| / create a release | 创建 Release | tag exists, needs publish |
| list releases | 列出 Release | review published versions |
| view / edit release | 查看/编辑 Release | metadata update |
| upload / download asset | 上传/下载资源 | binaries, archives |
| delete release | 删除 Release | rollback / mistake |
When NOT to Use
| Scenario | Why Not | Use Instead |
|---|---|---|
| Auto-generating changelog and version inference | This skill manages Release CRUD, not version decision or changelog generation | /gf-release-helper for SemVer inference + changelog + release creation |
| Creating Git tags | This skill requires tags to exist first, never creates them | git tag <v> + git push --tags for tag creation |
| Deleting without double confirmation | This skill requires two confirmations before irreversible deletion | Non-negotiable — always double-confirm tag before delete |
| Uploading non-existent files | This skill verifies file existence before upload | Verify file path exists before invoking upload |
| Running quality checks before release | This skill manages release metadata, not quality verification | /gf-quality for 6-gate quality check before release |
Core Pattern
gf auth status
git tag -l <tag>
gf release <subcommand> ...
Quick Reference
| Goal | Command |
|---|---|
| Create | gf release create --tag <tag> [--name <n>] [--body <b>] [--draft] [--prerelease] [--target <ref>] |
| List | gf release list |
| View | gf release view <tag> |
| Edit | gf release edit <tag> [--name <n>] [--body <b>] [--draft] [--prerelease] |
| Upload | gf release upload <tag> --file <path> [--asset-name <n>] |
| Download | gf release download <tag> --asset <name> [--dest <dir>] |
| Delete | gf release delete <tag> |
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 · 163 lines · 58 tokens per session scan A 504ad1c6f8f3
gf-release is a skill published in the GitHub repository byx-darwin/gitflow-cli (2 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 1,559 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.