execute

A workflow for completing beads tasks, where each task is broken into smaller steps that can be run and tracked independently.

In plain words
What is it for?
Use it to execute bugs, complex features, refactors, and well-defined maintenance tasks through reproduction, research, review, implementation, and verification steps.
Why use it?
It keeps research, decisions, and execution organised across a task, including when work is interrupted or the task needs bug investigation or test-driven development (TDD), a practice of writing tests before the implementation.

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/postindustria-tech/agentic-toolkit/execute
Any agent
npx skills add postindustria-tech/agentic-toolkit --skill execute
Clone the repo
git clone --depth 1 https://github.com/postindustria-tech/agentic-toolkit

Made for: Claude Code, Codex.

Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,832 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 $0.00114 $0.03832
Opus 5 $0.00057 $0.01916
Sonnet 5 $0.00023 $0.00766
Haiku 4.5 $0.00011 $0.00383

Measured yesterday against content hash 38f8329e3a41, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/cook_formula.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/dev-practices/skills/execute/SKILL.md · 325 lines

How it starts

The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Execution (Molecular)

Molecular workflow for executing beads tasks. Creates an atom graph where each step is independently executable and survives context compaction. Research findings are stored in the bead itself, making each task self-contained.

Args

/dev-practices-execute <task-id-1> [task-id-2] [task-id-3] ...

One or more beads task IDs. Each task gets atoms chained in sequence. Multiple tasks execute sequentially.

Formula Selection

Auto-select based on task type -- run bd show <id> to check the type and description:

Task Type Formula Atoms per task When to use
bug bug-triage.yaml 7 Bugs that need reproduction and root cause analysis
Complex tasks task-execute.yaml 7 Tasks needing research, architect review, or TDD (new features, refactors with unknowns)
Well-defined tasks task-single.yaml 3 Tasks with clear descriptions, known code paths, no design decisions (test rewrites, allowlist fixes, mechanical changes)

How to choose between task-execute and task-single:

  • Does the task need research (unfamiliar code, unknown APIs)? -> task-execute
  • Does the task need architect review (multiple valid approaches)? -> task-execute
  • Does the task need TDD red-green (new production code)? -> task-execute
  • Is the task self-contained (description says exactly what to do)? -> task-single
  • Is the task test-only (rewriting tests, not production code)? -> task-single
  • Is the task mechanical (remove from allowlist, update imports)? -> task-single

Test-first is enforced in task-execute and bug-triage:

  • Bugs: The reproduce atom requires a failing test before the fix atom proceeds
  • Tasks (task-execute): The write-test atom requires a failing regression test before implement proceeds
  • Refactors: write-test guards existing behavior with edge case tests before changes begin

task-single skips TDD because the work IS the test -- there's no separate production code to gate on. The execute atom runs the project quality command as the gate.

Read the full file on GitHub · 325 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. yesterday First seen · 325 lines · 114 tokens per session scan A 38f8329e3a41

Subscribe to this mod's changes

execute is a skill published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 3,832 once invoked, about $0.0006 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

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 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

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…

vercel/next.js · 170 tokens