execute

An executor that carries out an approved coding plan from start to finish. It assigns each step to a worker suited to its complexity and performs code reviews before delivery.

In plain words
What is it for?
Use it to implement a completed plan, including its planned code changes, verification, per-step reviews, and final review.
Why use it?
It coordinates implementation across multiple plan steps and keeps execution moving without requiring manual handoffs between waves of work. Reviews provide checks on both individual changes and the completed result.

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/anilcancakir/claude-code/execute
Any agent
npx skills add anilcancakir/claude-code --skill execute
Clone the repo
git clone --depth 1 https://github.com/anilcancakir/claude-code

Made for: Claude Code, Codex.

Per session 196 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,512 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00196 $0.09512
Opus 5 $0.00098 $0.04756
Sonnet 5 $0.00039 $0.01902
Haiku 4.5 $0.00020 $0.00951

Measured 2d ago against content hash 240606380199, 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 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

rendered state), not just `curl`. `curl` proves the endpoint answered; only the walk-through proves the surface works.
plugins/ac/skills/execute/SKILL.md · 521 lines

How it starts

The opening of the file, as written. The whole thing — 521 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ac:execute

Executor that runs an approved plan to completion. Auto-continue between waves: never asks "should I continue". Per-step manual code review is non-negotiable. Final code-review pair gates the deliver.

Plan: $ARGUMENTS

Standing rules

These hold for the whole run, including after a compaction. Everything below this block is procedure; these are the bounds. They sit here because a re-attached skill keeps only its first 5,000 tokens after compaction (https://code.claude.com/docs/en/skills.md) and this body is far larger, so a rule further down is gone from context on exactly the long runs that need it.

Turn termination. Your turn ends on exactly one of: an AskUserQuestion call, the Phase 4b execution summary, or a named BLOCKER from <auto_mode>. Nothing else ends it. Never end a turn by describing what you would do next, and never propose that the user open a fresh session to continue the run.

Every branch that terminates the run deletes .ac/state/active-execution.json first. That is not bookkeeping. While the marker exists, the plugin's Stop hook blocks the turn from ending and returns the outstanding step count to you (plugins/ac/hooks/stop-guard.sh); the marker's absence is what permits a stop.

Context. Auto-compaction summarizes older turns and the run continues. A filling context window is not a stopping condition, not a reason to hand the remainder back, and not a reason to suggest a new session. No compaction command is available to you: /compact is a local CLI command (commands/compact/index.ts:5 sets type: 'local'; tools/SkillTool/SkillTool.ts:421-427 rejects any command that is not prompt-based), so never plan around invoking it. When the procedure you need has been truncated away, re-invoke the ac:execute skill to restore this body, then read PLAN_PATH for the authoritative step state.

A stop needs a name. "I cannot verify this properly in the remaining context" is a stop wearing the clothes of a report. When a step genuinely cannot be completed to the plan's standard, the reason is one of: a fact you do not have and cannot obtain, a decision only the user can make, or a gate you cannot pass. Each maps to a BLOCKER branch (2i, 2j, 3d) that surfaces an AskUserQuestion and deletes the marker. Name the class, take the branch, report what did land. Never substitute a capacity limit for the real reason.

Read the full file on GitHub · 521 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 521 lines · 196 tokens per session scan A 240606380199

Subscribe to this mod's changes

execute is a skill published in the GitHub repository anilcancakir/claude-code (3 stars, last pushed 13d ago), licensed MIT. It adds 196 tokens to every session and 9,512 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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