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/st1page/agent-knowledge-framework/github-actionsnpx skills add st1page/agent-knowledge-framework --skill github-actionsgit clone --depth 1 https://github.com/st1page/agent-knowledge-frameworkWhat 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 | $0.00069 | $0.02018 |
| Opus 5 | $0.00034 | $0.01009 |
| Sonnet 5 | $0.00014 | $0.00404 |
| Haiku 4.5 | $0.00007 | $0.00202 |
Grade A, and why
github-actions scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -f https://example.com/api How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Actions 实战编写与调试
目标:快速编写正确的 GitHub Actions workflow,高效调试失败,理解平台行为边界。
实验仓库:
st1page/gh-actions-lab(9 个场景的完整 workflow 示例)
1. 触发方式速查
| 触发 | on: 写法 |
典型用途 |
|---|---|---|
| Push | push: { branches: [main], paths: ["src/**"] } |
CI |
| PR | pull_request: { branches: [main] } |
代码审查 |
| 定时 | schedule: [{ cron: "*/15 * * * *" }] |
周期任务 |
| 手动 | workflow_dispatch: { inputs: ... } |
按需触发 |
| API | repository_dispatch 或 gh workflow run |
外部集成 |
paths filter 边界:只匹配 push 事件中实际变更的文件;如果 commit 没改 src/** 下的文件,即使 push 到 main 也不触发。workflow_dispatch 触发时 paths filter 不生效。
cron 延迟:GitHub 不保证 cron 准时触发,高峰期可延迟 5–30 分钟。Cron 只在 default branch 生效。
2. Job 依赖与条件执行
needs DAG
jobs:
build: ...
test-unit:
needs: build # build 完成后才跑
test-integration:
needs: build # 与 test-unit 并行
deploy:
needs: [test-unit, test-integration] # 两个都过才 deploy
needs 形成 DAG,同层无依赖的 job 自动并行。
if 条件
# commit message 包含 [deploy] 时才执行
- if: contains(github.event.head_commit.message, '[deploy]')
# 仅 PR 事件
- if: github.event_name == 'pull_request'
# 前置 job 失败也要跑(清理/汇报)
jobs:
observer:
needs: [job_a, job_b]
if: always() # 不管前置结果都跑
concurrency 控制
concurrency:
group: deploy-${{ github.ref }}
cancel-in-progress: true # 新 run 自动取消旧 run
3. 重试策略
Step 级重试(nick-fields/retry)
- uses: nick-fields/retry@v3
with:
timeout_minutes: 2
max_attempts: 3
retry_wait_seconds: 5
command: |
# 可能偶发失败的命令
curl -f https://example.com/api
Run 级重跑
# 全量重跑(所有 job 重新执行)
gh run rerun <run-id>
# 仅重跑失败的 job(已成功的跳过)
gh run rerun <run-id> --failed
run_attempt 递增:每次 rerun,github.run_attempt +1(首次为 1)。可用于区分首次运行和重跑:
- run: echo "Attempt ${{ github.run_attempt }}"
Artifact 名中带 attempt 可追踪每次运行的产物差异。
4. Secret & Variable 注入
设置
gh secret set API_KEY --body "xxx" -R owner/repo
gh variable set DEPLOY_TARGET --body "staging" -R owner/repo
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 · 230 lines · 69 tokens per session scan A 57bf0124b02b
github-actions is a skill published in the GitHub repository st1page/agent-knowledge-framework (41 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 69 tokens to every session and 2,018 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…