execution

execution is a skill for Claude Code from Jamie-BitFlight/claude_skills. It costs 98 tokens per session (1,489 once invoked), scanned A, original, MIT.

A workflow stage that sends one ready development task to a fresh coding-agent session and checks the result.

In plain words
What is it for?
It is used to execute decomposed tasks, retry tasks that need work, and collect implementation results.
Why use it?
It keeps each worker focused on one complete task and catches failures through built-in quality checks.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the dh plugin — 53 skills, 28 agents shipped together

Good fit It is used to execute decomposed tasks, retry tasks that need work, and collect implementation results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jamie-bitflight/claude_skills/execution
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.

Any agent
npx skills add Jamie-BitFlight/claude_skills --skill execution
Clone the repo
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skills

Made for: Claude Code.

Or install dh, the plugin that ships this one along with the rest of its 53 skills, 28 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for execution

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/execution.svg)](https://agentmods.dev/skills/jamie-bitflight/claude_skills/execution)
Your own site
<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/execution"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/execution.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,489 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00098 $0.01489
Opus 5 $0.00049 $0.00745
Sonnet 5 $0.00020 $0.00298
Haiku 4.5 $0.00010 $0.00149

Measured 3d ago against content hash f4ae2837d4b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

execution 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 3d 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.

plugins/development-harness/skills/execution/SKILL.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SAM Stage 5 — Execution

Role

You are the execution dispatcher for the SAM pipeline. You launch fresh, stateless agent sessions to execute individual tasks. Each agent receives exactly one task as its complete context.

Core Principle

The task IS the prompt. Each executing agent gets a fresh session with zero memory of previous stages. Everything the agent needs is embedded in the task. If the task is insufficient, that is a Stage 4 defect, not a Stage 5 problem.

When to Use

  • After Stage 4 Task Decomposition produces ARTIFACT:TASK entries
  • For each task ready for execution (dependencies satisfied)
  • When re-executing a task after Stage 6 returns NEEDS_WORK

Process

flowchart TD
    Start([ARTIFACT:TASK]) --> R1[1. Read Task]
    R1 --> R2[2. Resolve role to agent]
    R2 --> R3[3. Dispatch to agent in fresh session]
    R3 --> R4[4. Agent executes task]
    R4 --> R5[5. Agent runs embedded verification]
    R5 --> BP[6. Deterministic backpressure]
    BP --> Q{Quality gates pass?}
    Q -->|Yes| Collect[7. Collect execution results]
    Q -->|No| Fix[Agent addresses quality failures]
    Fix --> BP
    Collect --> Done([ARTIFACT:EXECUTION])

Step 1 — Read Task (sam_task action=read)

Read the task via sam_task. The returned TaskAssignment model contains both plan-level context (plan_goal, plan_context, plan_acceptance_criteria) and the task body with YAML frontmatter.

Step 2 — Resolve Role to Agent

Call mcp__plugin_dh_backlog__profile_list() (no plugin filter) to fetch every installed agent's name, plugin, and description. Match the task's abstract role and its actual content (title, requirements, file paths) against the returned descriptions — assign whichever agent's declared capability has the strongest overlap.

If no agent's description plausibly matches, dispatch dh:task-worker. No specialist profile will be loaded — task-worker executes the task directly with full dh tool permissions.

Step 3 — Dispatch to Fresh Session

Read the full file on GitHub · 204 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. 3d ago First seen · 204 lines · 98 tokens per session scan A f4ae2837d4b3

Subscribe to this mod's changes

execution is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (65 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 1,489 once invoked, about $0.0005 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 2026-09-03.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 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