A command that creates a pull request, the review page for proposed code changes, from a completed feature's project records and Git history.

It is for preparing a feature pull request with a title, summary, story references, and a phase-by-phase breakdown. A target branch can be supplied; otherwise it uses `main`.

It removes the manual work of collecting the story, plan, commits, tests, and implementation phases into a consistent review description.

pr — Command by TouheedCode

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/touheedcode/claude-dev-workflow/pr

Clone the repo

git clone --depth 1 https://github.com/TouheedCode/claude-dev-workflow

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 584 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	$0.00000	$0.00584
Opus 5	$0.00000	$0.00292
Sonnet 5	$0.00000	$0.00117
Haiku 4.5	$0.00000	$0.00058

Measured yesterday against content hash ee14f68f3fba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr 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.

.claude/commands/pr.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pr — Create Pull Request with Phase Breakdown

Arguments

$ARGUMENTS — Optional: target branch (defaults to main)

Instructions

You are creating a pull request that summarizes all phase commits for a completed feature.

Input: $ARGUMENTS

Step 1: Gather Context

Read .phase-context.json for the story ID and completed phases
Read the user story at docs/stories/{story-ID}.md for the feature description
Read the plan at docs/plans/PLAN-{story-ID}.md for the phase breakdown
Run git log main..HEAD --oneline to get all commits on this branch

Step 2: Generate PR Content

Create the PR with this structure:

Title: feat: {story title} (under 72 characters)

Body:

## Summary

{2-3 sentence description of what this feature does, written for a code reviewer}

## Story Reference

- Story: {story-ID} — {title}
- PRD: {PRD file path}

## Phase Breakdown

### Phase 1: Presentational UI ✅
- Built: {component list}
- Tests: {count} unit tests

### Phase 2: API Client & Mocks ✅
- Hooks: {hook list}
- MSW handlers: {handler list}
- Shared types: {type list}

### Phase 3: Smart Components ✅
- Pages: {page list}
- Stores: {store list}
- Tests: {count} integration tests

### Phase 4: Repository Layer ✅
- Schema: {table list}
- Repositories: {repo list}
- Tests: {count} with Testcontainers

### Phase 5: Service Layer ✅
- Services: {service list}
- Tests: {count} with mocked repos

### Phase 6: Controller Layer ✅
- Endpoints: {endpoint list}
- Tests: {count} E2E tests

### Phase 7: Integration ✅
- MSW mocks removed for production paths
- E2E verification passing

## Test Plan

- [ ] All unit tests pass (`npm run test`)
- [ ] All E2E tests pass (`npm run test:e2e`)
- [ ] Lint clean (`npm run lint`)
- [ ] Type check clean (`npm run typecheck`)
- [ ] Manual smoke test of primary user flow
- [ ] Verify no MSW handlers leak into production

## BDD Scenarios Covered

{List each scenario from the user story with ✅}

Step 3: Create the PR

Read the full file on GitHub · 89 lines

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 · 89 lines · 0 tokens per session scan A ee14f68f3fba

Subscribe to this mod's changes

pr is a command published in the GitHub repository TouheedCode/claude-dev-workflow (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 584 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.

Code review Git and workflow Productivity agentic-coding ai-agent ai-coding ai-workflow anthropic best-practices

pr

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/pr — Create Pull Request with Phase Breakdown

Arguments

Instructions

Step 1: Gather Context

Step 2: Generate PR Content

Step 3: Create the PR

What this file has done since we first saw it

Other commands, from other repositories

auto-work

develop-review

developing

manual-work

plan-review

analyze