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/hybridaione/hybridclaw/github-pr-workflownpx skills add HybridAIOne/hybridclaw --skill github-pr-workflowgit clone --depth 1 https://github.com/HybridAIOne/hybridclawWrote 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/hybridaione/hybridclaw/github-pr-workflow)<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/github-pr-workflow"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/github-pr-workflow.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.00893 |
| Opus 5 | $0.00014 | $0.00447 |
| Sonnet 5 | $0.00006 | $0.00179 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
github-pr-workflow 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub PR Workflow
Use this skill for the end-to-end pull request loop from branch creation through merge readiness.
Default Sequence
- Verify GitHub CLI authentication if the workflow will use
gh. - Sync the base branch.
- Create a focused branch for one change.
- Implement and validate locally.
- Commit with a clear message.
- Push and open or update the PR.
- Check CI and fix failures.
- Address review feedback.
- Merge only when the branch is green and approved.
Core Commands
Verify GitHub CLI Auth
gh auth status
Run this before any git or PR workflow steps that depend on gh. If it fails,
fix authentication first so the workflow does not stop later during gh pr create,
gh pr checks, or other PR commands.
Prepare the Branch
git fetch origin
git checkout main
git pull --ff-only origin main
git checkout -b feat/short-description
Use the repository's actual base branch if it is not main.
Commit Clearly
git status --short
git add path/to/file.ts tests/path/to/file.test.ts
git commit -m "feat: short summary"
Keep commits scoped and explain user-visible intent in the subject line.
Push and Open the PR
git push -u origin HEAD
gh pr create --fill
When --fill is not enough, make the body explicit with:
- summary
- test plan
- risks or rollout notes
- linked issue or ticket
Useful variants:
gh pr create --draft
gh pr create --base main --title "feat: short summary" --body-file /tmp/pr-body.md
gh pr view --web
If gh is unavailable, complete the local git steps and use the GitHub UI for
PR-specific actions.
CI and Merge Readiness
Check status after every push:
gh pr checks
gh pr checks --watch
gh run list --branch "$(git branch --show-current)" --limit 5
gh run view <run-id> --log-failed
When a check fails:
- inspect the failing job or logs
- reproduce locally if possible
- fix the smallest confirmed problem
- rerun targeted validation
- push again and re-check CI
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 First seen · 157 lines · 28 tokens per session scan A 64dd4aea050b
github-pr-workflow is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 893 once invoked, about $0.0001 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
m3-health
Health check — package version, installed payload, chatlog DB row count, per-agent hook state.
m3-help
List all m3-memory slash commands / skills and what they do.
m3-forget
Delete a memory permanently. Asks for confirmation first.
m3-search
Hybrid memory search — FTS5 + semantic vector + MMR diversity rerank.
m3-status
Chatlog subsystem status — row counts, queue depth, spill, last capture, hook health.
m3-notify
Poll the inbox for new notifications addressed to you.