workflow

A multi-phase development workflow that carries a planned task from implementation through pull request, review, summary, and archiving. It can pause between phases or run them automatically.

In plain words
What is it for?
Use it to execute checklist items with test-driven development (write a failing test, make it pass, then commit), open pull requests, run reviews, and move through the phases of an active plan.
Why use it?
It removes the need to coordinate each stage of a large, phased task by hand. It also keeps work for each phase separated in its own branch and worktree.

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/brian-lai/para-programming-plugin/workflow
Any agent
npx skills add brian-lai/para-programming-plugin --skill workflow
Clone the repo
git clone --depth 1 https://github.com/brian-lai/para-programming-plugin

Made for: Claude Code, Codex.

Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,130 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 $0.00012 $0.01130
Opus 5 $0.00006 $0.00565
Sonnet 5 $0.00002 $0.00226
Haiku 4.5 $0.00001 $0.00113

Measured 2d ago against content hash de6e0406ff02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

skills/workflow/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrate the full PARA execution cycle across phases: execute → PR → review → summarize → archive → next phase. Supports both manual (pause at boundaries) and autonomous (--auto) modes.

Usage

/para:workflow                     # Run workflow for active plan (pause at phase boundaries)
/para:workflow --auto              # Fully autonomous (no pause between phases)
/para:workflow --phase=N           # Start from a specific phase
/para:workflow --skip-review       # Skip Staff+ review loops (for speed)

Prerequisites

  • context/context.md must exist with an active phased plan
  • For simple (non-phased) plans, use /para:execute directly — the workflow command is designed for multi-phase orchestration
  • Git repository must be clean (or user confirms proceeding with dirty state)

Process (Per Phase)

For each phase in the plan, the workflow runs these steps in order:

Step 1: Execute

Run /para:execute --phase=N.

  • Creates a worktree and branch for the phase
  • Extracts checklist items as todos
  • Implements each todo following the TDD cycle (red → green → commit)
  • Each checklist item text becomes the commit message

Step 2: Create PR

Create a pull request for the phase branch. This step owns PR creation for workflow runs. /para:summarize (Step 4) will detect that it's running inside the orchestrator and skip its standalone push/PR guidance.

  • PR title: para/{task-name} phase N: {phase title}
  • PR body: auto-generated from:
    • Phase objective (from sub-plan)
    • Commit list with descriptions
    • Checklist of implementation steps (checked off)
    • Link to plan file

Step 3: Review

Run /para:review --pr (unless --skip-review is specified).

  • Staff+ subagent reviews the PR
  • Loop until approved (or user overrides)
  • Apply fixes, create additional commits as needed
  • Push fixes to the PR branch

Step 4: Summarize

Run /para:summarize --phase=N.

  • Generate phase summary to context/summaries/
  • Record what changed, rationale, key learnings
  • Mark phase as "completed" in context/context.md

Read the full file on GitHub · 126 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.

  1. 2d ago First seen · 126 lines · 12 tokens per session scan A de6e0406ff02

Subscribe to this mod's changes

workflow is a skill published in the GitHub repository brian-lai/para-programming-plugin (7 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 1,130 once invoked, about $0.0001 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens