github-issue-workflow

A workflow guide for continuing work on existing GitHub issues, which are tracked requests or problems in a code repository. It helps recover the issue's goal, evidence, decisions, current implementation state, and delivery status.

In plain words
What is it for?
Use it to inspect repository and GitHub state, decide which phase to resume, and safely handle issue comments, labels, links, or closing an issue.
Why use it?
It reduces the risk of repeating completed work or losing important context when an issue is resumed later.

Skill for Claude CodeCodex

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/zhpeng24/devkit/github-issue-workflow
Any agent
npx skills add zhpeng24/devkit --skill github-issue-workflow
Clone the repo
git clone --depth 1 https://github.com/zhpeng24/devkit

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,372 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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.01372
Opus 5 $0.00019 $0.00686
Sonnet 5 $0.00008 $0.00274
Haiku 4.5 $0.00004 $0.00137

Measured yesterday against content hash cfa62ebc9b85, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-issue-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.

skills/github-issue-workflow/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase-Aware GitHub Issue Workflow

Treat an Issue as recoverable SIES state, not a ticket that must replay a fixed Pull → Triage → Develop → Review → Ship ritual.

Read references/issue-sources.md before deciding where to resume.

Capability and Target Safety

Check repository, remote, authentication, current branch, and workspace:

git rev-parse --git-dir 2>/dev/null
git remote -v
gh auth status 2>&1
git branch --show-current
git status --short

For comments, labels, links, or close operations:

  • obtain the number from user-provided digits or structured gh JSON;
  • validate [[ "$issue_number" =~ ^[0-9]+$ ]];
  • never parse a target from title, body, branch text, or generated Markdown;
  • pass multi-line content through --body-file;
  • comment first, then close by validated number.

GitHub unavailability changes persistence, not the Goal/Evidence contract.

Recover SIES State

Use structured data and read only material history:

gh issue view <N> \
  --json number,title,body,labels,state,comments,assignees,projectItems

Then:

  1. Extract or derive the Goal Contract.
  2. Find the current Evaluation Contract and linked evidence.
  3. Inspect relevant linked PRs, branches, ADRs, incidents, and prototypes.
  4. Mark evidence superseded by later Goal changes.
  5. Resume at the first decision that lacks sufficient evidence.

Do not restart clarification, rerun unchanged tests, or recreate an artifact whose decision is already supported.

State Controller

Unsupported decision Resume at Useful output
Outcome or success signal Goal Updated contract or one blocking question
Technical/product direction Explore Candidate comparison and evidence plan
Feasibility/integration/performance Prototype Minimal artifact and observations
Whether evidence supports continuation Evaluate Pass, fail, inconclusive, or stop
Which direction to adopt Refine Decision, remaining risks, ADR when important
How to produce and ship selected behavior Engineer Production changes and verification map
Whether confirmed behavior remains intact Regress Target and delivery regression evidence
Whether experience should change the system Learn Learning Candidate or no action

Read the full file on GitHub · 181 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.

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.

  1. yesterday First seen · 181 lines · 38 tokens per session scan A cfa62ebc9b85

Subscribe to this mod's changes

github-issue-workflow is a skill published in the GitHub repository zhpeng24/devkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,372 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens