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/executenpx skills add brian-lai/para-programming-plugin --skill executegit 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 | $0.00015 | $0.01632 |
| Opus 5 | $0.00008 | $0.00816 |
| Sonnet 5 | $0.00003 | $0.00326 |
| Haiku 4.5 | $0.00002 | $0.00163 |
Grade A, and why
execute 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute the active plan by creating an isolated worktree and tracking todos. Supports both simple and phased plans.
Usage
/para:execute # Auto-detect plan; prompts for phase if phased
/para:execute --phase=N # Execute specific phase
/para:execute --no-worktree # Skip worktree creation; fall back to git checkout -b
What It Does
- Read the active plan from
context/context.md - Detect simple vs phased plan (presence of
phased_executionin JSON) - For phased plans, determine which phase to execute (prompt if not specified; verify previous phases are completed)
- Fetch latest and create an isolated git worktree:
git fetch origin main && git worktree add .para-worktrees/{task-name} -b para/{task-name} origin/main(orpara/{task-name}-phase-N) - Extract checkbox items (
- [ ] ...) from the plan's Implementation Steps section as todos. The checkbox text becomes both the todo item and the eventual commit message. - Update
context/context.mdwith the todo list and worktree path (this file lives in the main working tree) - Make an empty initial commit in the worktree (see "context/context.md lives in main tree" design note below the Commit-Per-Todo Rule section):
git -C .para-worktrees/{task-name} commit --allow-empty -m "chore: Initialize execution context for {task-name}"
--no-worktree Escape Hatch
When --no-worktree is specified, fall back to the legacy branch-based behavior: git checkout -b para/{task-name}. This still creates a branch — it just switches your current working directory to that branch instead of creating a separate worktree directory. There is no isolation: your main working tree moves to the new branch. Use this only for single-developer workflows where you don't need to keep the main working tree on its current branch.
Prerequisites
context/context.mdmust exist with an active plan- If no active plan, error: "No active plan found. Run
/para:planfirst." - If dirty git state, warn user and offer to continue or stash first
- Check
.gitignorefor.para-worktrees/entry; if missing, warn and suggest running/para:init - If target worktree directory already exists, ask: continue in it, remove and recreate, or cancel
- If target branch already exists but no worktree, use
git worktree add .para-worktrees/{task-name} para/{task-name}(without-b)
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 · 121 lines · 15 tokens per session scan A 26471812c85c
execute is a skill published in the GitHub repository brian-lai/para-programming-plugin (7 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 1,632 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…