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.
npx agentmods add skills/brian-lai/para-programming-plugin/workflownpx skills add brian-lai/para-programming-plugin --skill workflowgit clone --depth 1 https://github.com/brian-lai/para-programming-pluginWhat 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 | $0.00012 | $0.01130 |
| Opus 5 | $0.00006 | $0.00565 |
| Sonnet 5 | $0.00002 | $0.00226 |
| Haiku 4.5 | $0.00001 | $0.00113 |
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.
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.mdmust exist with an active phased plan- For simple (non-phased) plans, use
/para:executedirectly — 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
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.
- 2d ago First seen · 126 lines · 12 tokens per session scan A de6e0406ff02
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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…
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.
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.