A command for carrying out an approved implementation plan from start to finish. It can run plan phases in sequence, verify the result, retry one debugging cycle after a verification failure, and create task-level commits.

Use it to execute a plan file or a directory of approved phases, resume interrupted work, enable autonomous execution, and optionally skip pushing commits.

It removes the need to manually pause between approved tasks and keeps execution tied to a defined plan. It also stops when verification still fails or when an architectural decision needs the user’s input.

execute — Command for Claude Code by anilcancakir/claude-code-plugin

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.

Clone the repo

git clone --depth 1 https://github.com/anilcancakir/claude-code-plugin

Made for: Claude Code.

Or install ac, the plugin that ships this one along with the rest of its 6 skills, 9 commands, 2 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/anilcancakir/claude-code-plugin/execute/github.svg)](https://agentmods.dev/commands/anilcancakir/claude-code-plugin/execute)

Your own site

<a href="https://agentmods.dev/commands/anilcancakir/claude-code-plugin/execute"><img src="https://agentmods.dev/badge/commands/anilcancakir/claude-code-plugin/execute/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/anilcancakir/claude-code-plugin/execute"><img src="https://agentmods.dev/badge/commands/anilcancakir/claude-code-plugin/execute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,548 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.

Model	Per session	Once invoked
Fable 5.1	$0.00046	$0.04548
Opus 5.5	$0.00018	$0.01819
Sonnet 5.5	$0.00009	$0.00910
Haiku 4.5	$0.00005	$0.00455

Measured 1mo ago against content hash 926eca773033, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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/ac/commands/execute.md · 339 lines

How it starts

The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute

Run an approved plan to completion in the main agent. Loop mode: do not pause between Tasks. Halt only on verify-fail after one debug retry, or on Rule 4 architectural asks.

Phase 1: Load

Parse $ARGUMENTS:
- .md path: single-file plan or a specific Mode B phase file.
- Directory path (ends with / or <slug>/): Mode A, execute every approved phase sequentially.
- Empty: Glob .ac/plans/**/*.md, filter status: approved, pick the most recent. AskUserQuestion if more than one.
- Strip flags before resolving the path:
  - --force: allow re-running a status: complete plan.
  - --no-push: commit locally per Task but skip git push.
  - --auto: enter autonomous mode. Sticky, written to the state file, propagates across resumes and across remaining phases.
  - --no-auto: leave autonomous mode. Clears the state file's autonomous: true. Useful mid-flight when the user wants to take manual control again.
  - --max-iterations=N: cap the autonomous resume loop. Default 100. Override with --max-iterations=999 for effectively unbounded runs.
  - --resume <slug>: resume an executing plan from its state file. See step 5.
Read the target. Validate frontmatter:
- status: approved or status: executing: proceed.
- status: complete without --force: refuse with Plan already complete. Add --force to re-run.
- status: draft: refuse with Plan not approved. Run /ac:plan <slug> first.
State file resolution. State path is the schema location from plugins/ac/references/execution-state-schema.md:
- Simple: .ac/plans/<slug>.execution-state.md.
- Mode A or B: .ac/plans/<slug>/.execution-state.md.
- On first run (no state file yet): create it with iteration: 1, autonomous: <true if --auto else false>, max_iterations: <flag value or 100>, current_phase: 1, current_task: 1, attempt: 1, status: executing, started_at: <now>.
- On subsequent runs (state file exists): load frontmatter. If --auto was passed now, set autonomous: true. If --no-auto, set it to false. If neither, keep the stored value. Mid-flight switching is supported, the new value applies from the next Task forward.
- If --max-iterations=N is passed, overwrite the stored cap.

Read the full file on GitHub · 339 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.

1mo ago First seen · 339 lines · 46 tokens per session scan A 926eca773033

Subscribe to this mod's changes

execute is a command published in the GitHub repository anilcancakir/claude-code-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 4,548 once invoked, about $0.0002 per session on Opus 5.5. 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.

Claude Code Multi-Agent Orchestration Planning development-twin plan-first

perf-difficult-conversation

Three-conversations framework rehearsal (Stone/Patton/Heen — Harvard Negotiation Project) for high-stakes conversations — termination, demotion, hard feedback, conflict surfacing. Produces three-conversations breakdown (what-happened / feelings / identity), conversation script with multiple opening choices, SCARF…

frankxai/Starlight-Intelligence-System · 93 tokens

culture-onboarding-90

Design a 90-day onboarding architecture for a role. First day (psychological safety + belonging activation), first week (relationship + role context + early wins), first month (skill ramp + integration + baseline), first quarter (autonomous performance + cultural integration check). Written-first elements for…

frankxai/Starlight-Intelligence-System · 101 tokens

perf-coaching-protocol

Generate a 60-minute solution-focused + CBT-grounded coaching session script for a manager-as-coach engagement. Coaches use questions, not advice. Produces session structure (check-in → focus → scaling → exception-finding → small-step → close), follow-up prompts, and the manager-as-coach training notes that name the…

frankxai/Starlight-Intelligence-System · 83 tokens

reclaim-knowledge

Organize scattered professional material into a domain-based second-brain architecture. Maps existing sources (Canva, Drive, local folders, Notion, screenshots) to functional domains. Non-technical-friendly — produces folder structure + drag-and-drop instructions, not CLI commands.

frankxai/Starlight-Intelligence-System · 58 tokens

design-regimen

Design an integrated weekly regimen — training, nutrition, sleep, stress, recovery — matched to the person's actual life. Composes with gym-training-expert and health-nutrition-expert for domain detail. Produces a sustainable architecture, not an extreme program. Not medical advice.

frankxai/Starlight-Intelligence-System · 60 tokens

hire-calibrate

Run the pre-loop calibration session — 60 minutes with ≥3 raters, review the rubric, score 2 anchor candidates the team has previously seen, surface inter-rater drift, agree on hire-bar examples. The calibration session itself is the deliverable. Without it, the loop runs on uncalibrated rulers. Per Project Oxygen …

frankxai/Starlight-Intelligence-System · 86 tokens