develop

A command that runs an automated development pipeline for a GitHub issue, a tracked software task.

In plain words
What is it for?
Use it to develop an issue through a sequence that runs code changes, linting, tests, builds, review, retries when needed, and a draft pull request.
Why use it?
It coordinates planning, implementation, testing, review, fixes, verification, and draft pull-request creation in one process.

Command for Claude Code

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 commands/let-sunny/canicode/develop
Clone the repo
git clone --depth 1 https://github.com/let-sunny/canicode

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 488 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 $0.00000 $0.00488
Opus 5 $0.00000 $0.00244
Sonnet 5 $0.00000 $0.00098
Haiku 4.5 $0.00000 $0.00049

Measured 2d ago against content hash 4b3396c803fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

develop 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 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.

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.

.claude/commands/develop.md · 52 lines

What it actually says

Run the automated development pipeline for a GitHub issue.

Input: $ARGUMENTS (issue number, or --resume <run-dir> with optional --from <step>)

Instructions

Run the development script:

npx tsx scripts/develop.ts $ARGUMENTS

The script (scripts/develop.ts) orchestrates:

  1. Plan (Agent) — Read issue, explore codebase, produce plan.json
  2. Implement (Agent) — Write code per plan, commit, produce implement-log.json
  3. Test (CLI, non-blocking) — pnpm lint && pnpm test:run, failures forwarded to Review
  4. Review (Agent) — Independent review with intent-conflict awareness
  5. Fix (Agent) — Fix review findings while preserving implementation intent
  6. Verify (CLI + circuit breaker) — pnpm lint && pnpm test:run && pnpm build, auto-retry with re-plan
  7. PR (CLI) — gh pr create --draft

State tracked in logs/develop/<issue>--<timestamp>/index.json.

After the script completes

Report the summary from index.json:

  • Which steps completed, skipped, or failed
  • Plan summary and task count
  • Review verdict and finding counts
  • Circuit breaker state (if verify needed retries)
  • PR URL (if created)
  • Path to the run directory

Examples

# New run
npx tsx scripts/develop.ts 236

# Resume from failure
npx tsx scripts/develop.ts --resume logs/develop/236--2026-04-16-1200

# Resume from specific step (name or 1-based index: plan=1, implement=2, test=3, review=4, fix=5, verify=6, pr=7)
npx tsx scripts/develop.ts --resume logs/develop/236--2026-04-16-1200 --from review

Rules

  • The script handles all orchestration — do NOT manually run individual steps.
  • If the script fails, check $RUN_DIR/index.json for the failed step and error.
  • To re-run from a specific step, use --resume with --from.
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. 2d ago First seen · 52 lines · 0 tokens per session scan A 4b3396c803fa

Subscribe to this mod's changes

develop is a command published in the GitHub repository let-sunny/canicode (10 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 488 tokens. 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.