What is github-workflow?

An automated workflow connecting GitHub issues and pull requests to the steps from planning through merging code. It reacts to GitHub events and scheduled checks to plan work, monitor changes, fix CI (automated tests and checks), validate staging, and learn after merges.

Use it to install and operate an issue-to-merge process for a GitHub repository, including planning, implementation, review, CI fixes, staging validation, and post-merge follow-up.

It removes much of the manual coordination needed to move repository work from an issue to a merged change. It also provides checks for prerequisites, testing, monitoring, and workflow tuning.

github-workflow — Skill by suyoumo

Install

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.

agentmods

npx agentmods add skills/suyoumo/clawprobench/github-workflow

Any agent

npx skills add suyoumo/ClawProBench --skill github-workflow

Clone the repo

git clone --depth 1 https://github.com/suyoumo/ClawProBench

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 996 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00045	$0.00996
Opus 5	$0.00023	$0.00498
Sonnet 5	$0.00009	$0.00199
Haiku 4.5	$0.00005	$0.00100

Measured yesterday against content hash 0e730ca5e2ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-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 yesterday.

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.

ironclaw/skills/github-workflow/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Workflow Automation

Install and maintain a complete issue-to-merge workflow for any GitHub repository. Maps GitHub webhook events and cron schedules into automated missions for planning, implementation, review, CI fixing, staging validation, and post-merge learning.

Workflow

Gather project parameters from projects/<owner>-<repo>/project.md or ask the user.
Verify runtime prerequisites.
Install or update mission set from templates.
Run a dry test with event_emit.
Monitor outcomes and tune prompts/filters.

Parameters

Read these from the project file in workspace, or collect from the user:

repository: owner/repo (required)
maintainers: GitHub handles allowed to trigger implement/replan actions
staging_branch: default staging (or null if no staging workflow)
main_branch: default main
batch_interval_hours: default 8

Prerequisites

Before installing missions, verify:

GitHub skill authenticated (for issue/PR/comment/status operations).
GitHub webhook delivery configured to POST /webhook/tools/github.
Webhook HMAC secret configured in the secrets store as github_webhook_secret.
Events can also be emitted via event_emit tool for testing.

Install Procedure

Open workflow-routines.md.
For each template block:
- Replace placeholders ({{repository}}, {{maintainers}}, branch names)
- Namespace mission names with the repo slug (e.g. wf-issue-plan-nearai-ironclaw)
- Call mission_create with name, goal (the prompt), and cadence (cron expression or event:<pattern>)
If a mission already exists (check mission_list), update rather than duplicate.
If staging_branch is null, skip wf-staging-batch-review.
Write installation status to projects/<owner>-<repo>/project.md.
Confirm install with mission_list.

Mission Set

Install these missions per repository:

wf-issue-plan-<slug>: on issue.opened or issue.reopened, generate implementation plan comment.
wf-maintainer-gate-<slug>: on maintainer comments, decide update-plan vs start implementation.
wf-pr-monitor-<slug>: on PR open/sync/review-comment/review, address feedback and refresh branch.
wf-ci-fix-<slug>: on CI status/check failures, apply fixes and push updates.
wf-staging-review-<slug>: every N hours, review ready PRs, merge into staging, run batch correctness analysis, fix findings, then merge staging to main.
wf-learning-<slug>: on merged PRs, extract mistakes/lessons and write to shared memory.

Read the full file on GitHub · 104 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/workflow-routines.md 2.9 KB

Changes

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.

yesterday First seen · 104 lines · 45 tokens per session scan A 0e730ca5e2ed

Subscribe to this mod's changes

github-workflow is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 7d ago), licensed Apache-2.0. It adds 45 tokens to every session and 996 once invoked, about $0.0002 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.

Code review Evaluation Git and workflow LLM Testing agent benchmark harness leaderboard

lastlight-evals

Scaffold, configure and run a Last Light EVALS workspace — the harness that runs Last Light's real workflows against a mocked GitHub and grades them deterministically. Use when the user wants to "set up / scaffold Last Light Evals", "create an evals workspace or instance", "run evals", "compare models", or author new…

nearform/lastlight · 185 tokens

Evaluation

Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.

agentic-in/elephant-agent · 25 tokens

open-code-review

Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…

alibaba/open-code-review · 98 tokens

harness-creator

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…

walkinglabs/learn-harness-engineering · 142 tokens

gh-pr-description

Drafts and reviews GitHub pull request descriptions for the eve repository. Use when opening, updating, or reviewing a PR, or when summarizing a branch for reviewers.

vercel/eve · 38 tokens

technical-writing

Write, edit, review, or audit user-facing documentation for the eve repository. Use for changes under docs/, documentation tied to eve APIs or CLI behavior, docs work based on Slack or support feedback, and requests to make eve docs clearer, more natural, or less AI-patterned while verifying claims against current…

vercel/eve · 78 tokens