Every issue becomes a self-contained work order.
issuedev turns each GitHub issue into something typed, structured, and enriched with acceptance criteria — then resolves it, with commit messages and PR titles that link every line of code back to the intention that created it.
Structure, don't guess — plus the right model mode for the job
Describe a bug or feature in plain text. issuedev classifies the type, estimates effort (XS–XL), generates acceptance criteria, and files a clean issue — preserving your original words in a Reporter Context block without guessing implementation details.
⚡ Model: Each issue gets an advisory Suggested model with thinking level (e.g. GPT-5.5 High · Opus 4.8 Medium) keyed off effort, using CursorBench benchmarks — so you pick a capable tier for hard work and a cheaper tier for trivial fixes instead of running everything on max.
Issue → tested PR, one command
A 6-step pipeline runs end to end: preflight, research, plan, implement, QA, deliver. Out comes an atomic PR with Closes #N — branch named, commits conventional, tests written.
See the whole backlog at once
Dependency graph, priority suggestions, parallelizable work, stale-issue warnings, and already-fixed detection by scanning commits and PRs. One command produces a suggested execution order.
Hands-free, conservative by default
Triage → resolve → review → merge, looped across the backlog. Clean PRs merge; partial ones stay open for review unless you opt into aggressive mode. Dependency-aware merge gate keeps order sane.
Right model, right thinking level — stamped on every issue
When you create or normalize an issue, /issue-creator maps estimated effort to a model + thinking tier from CursorBench data. The preview shows ⚡ Model:; the issue body stores an advisory Suggested model: line with the benchmark date.
Use it to route XS typo fixes to low-cost modes and reserve extra-high thinking for large features — without blocking creation if the cache is offline (bundled seed + graceful fallback).
| Effort | OpenAI | Anthropic |
|---|---|---|
| XS | GPT-5.5 Low | Opus 4.7 Low |
| S | GPT-5.5 Medium | Opus 4.8 Low |
| M | GPT-5.5 High | Opus 4.8 Medium |
| L | GPT-5.5 Extra High | Opus 4.7 Extra High |
| XL | GPT-5.5 Extra High | Fable 5 Max |
Toggle with model_suggestion.enabled in .gitissue.yml · refresh CursorBench into .gitissue/model-data.json
From a sentence to a merged PR — in four moves.
No new platform to learn. The structured issue format is plain GitHub markdown, and every step is a command you run in the terminal you already live in.
Describe
Type the problem in plain English. /issue-creator classifies it, estimates effort, suggests model + thinking level, and structures a typed issue with acceptance criteria.
Triage
/issue-triage maps dependencies across the backlog, flags stale and already-fixed issues, and proposes an order.
Resolve
/issue-resolver N researches, plans, implements, and QAs — then opens an atomic PR that closes the issue.
Review & ship
/issue-pr-review verifies each acceptance criterion, scores five dimensions, fixes, and merges when green.
Transparency, not a black box.
Confidence scores, step progress, and exactly what's happening at each phase — straight from your terminal. Every symbol carries meaning.
Eight commands. One source of truth.
Each is a self-contained skill — drop it into Claude Code, Codex CLI, or any SKILL.md-compatible harness. Mix and match; nothing depends on the rest. Need exact inputs? See the full docs.
Classify type, estimate effort, suggest model + thinking level (CursorBench), preserve reporter context, and file structured acceptance criteria.
Root cause, git history, implementation options, complexity and risk — saved to .gitissue/.
6-step pipeline: preflight → research → plan → implement → QA → deliver a PR with Closes #N.
Dependency graph, stale detection, already-fixed scanning, priority and execution order.
Lint/format/test pre-pass, per-criterion AC verification, five-dimension scoring, and fix cycles. Auto-merge only with --auto.
Triage → resolve → review → merge loop with conservative-by-default merge modes.
Auto-detect language, framework, and test runner; generate a tuned .gitissue.yml.
Read-only health check for your IDD repository invariants. (maintainer tooling)
Two names for one idea: issues as the atomic unit of work.
Every change starts as a structured issue and ends as a PR linked to it. The methodology is plain markdown — issuedev just automates the translation.
The translation gap
Turning a vague report — "login is broken on mobile" — into a structured work order with acceptance criteria, current-code analysis at execution time, and a clear definition of done. That's the gap between describing a problem and shipping a fix, and IDD automates it.
The intention gap
Helping creators discover and articulate what they actually want through iterative refinement — so the commit that resolves an issue carries the why forward. Your git history becomes a knowledge base, not noise.
Works with the tools you already use.
IDD is a methodology, not a platform. The structured issue format is plain GitHub markdown — anything that reads issues can consume it. issuedev adds structure; everything else keeps working exactly as before.
Your first issue in 30 seconds.
Needs gh 2.0+, Git 2.30+, and Claude Code (or any SKILL.md agent). Zero config to start.
Questions, answered.
Does this lock me into a specific AI tool? +
Will it rewrite or overwrite my existing issues? +
> Reporter Context blockquote and posts a backup comment before changing anything. Inferred fields are tagged with confidence markers — (high confidence), (needs review) — so you can see exactly what was guessed versus what was certain.Is auto-pilot safe to run on a real repo? +
aggressive mode. A dependency-aware merge gate respects Depends on #N / Blocked by #N, and you can pass an explicit issue list for targeted runs.Do I need to configure anything to start? +
/init-gitissue to generate a project-specific .gitissue.yml — but it's entirely optional.What does it actually require? +
gh) 2.0+ authenticated via gh auth login, Git 2.30+, and Claude Code or any SKILL.md-compatible agent. Every gh call uses explicit JSON field selection — no fragile text parsing.How much does it cost? +
What is the suggested model on new issues? +
/issue-creator estimates issue effort (XS–XL) and adds an advisory Suggested model with a thinking level (e.g. GPT-5.5 High · Opus 4.8 Medium), grounded in CursorBench benchmarks. It appears in the create preview as ⚡ Model: and in the issue metadata so humans and agents can match spend to scope — use a low tier for trivial fixes and higher thinking only when the issue warrants it. Disable via model_suggestion.enabled: false in .gitissue.yml.Stop translating issues by hand.
Let your agents execute them.
Turn vague reports into agent-ready work orders — and turn your git history back into the knowledge base it was meant to be.