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/changoo89/claude-pilot/execute-plannpx skills add changoo89/claude-pilot --skill execute-plangit clone --depth 1 https://github.com/changoo89/claude-pilotWrote 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.
[](https://agentmods.dev/skills/changoo89/claude-pilot/execute-plan)<a href="https://agentmods.dev/skills/changoo89/claude-pilot/execute-plan"><img src="https://agentmods.dev/badge/skills/changoo89/claude-pilot/execute-plan.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00032 | $0.01706 |
| Opus 5 | $0.00016 | $0.00853 |
| Sonnet 5 | $0.00006 | $0.00341 |
| Haiku 4.5 | $0.00003 | $0.00171 |
Grade A, and why
execute-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Execute Plan (Plan Execution Workflow)
Purpose: Execute plans using TDD + Ralph Loop with parallel execution Target: Coder Agent implementing Success Criteria from plans
When to Use: Execute plans from /01_confirm, implement SCs with TDD, parallel execution of independent SCs, worktree mode for isolated development
Quick Reference:
PROJECT_ROOT="$(pwd)"
PLAN_PATH="$(find "$PROJECT_ROOT/.pilot/plan/pending" "$PROJECT_ROOT/.pilot/plan/in_progress" -name "*.md" -type f 2>/dev/null | sort | head -1)"
# Spawn teammate for SC execution
Spawn teammate "sc1-impl" with prompt: "You are a coder (see agents/coder.md).
Execute SC-1 from $PLAN_PATH. Skills: tdd, ralph-loop, vibe-coding.
Mark task done when complete. Message lead if blocked."
Scope: Plan detection, SC dependency analysis, parallel execution, worktree mode, GPT delegation. Team Lead operates in delegate mode (coordinate only, never implement). TDD/Ralph/Vibe → teammate skills.
Execution Steps
⚠️ EXECUTION DIRECTIVE: Execute ALL steps IMMEDIATELY. NEVER move plan to done/ (only /03_close has this authority), do NOT call close-plan automatically, plan MUST remain in .pilot/plan/in_progress/
Team Lead Role: Operate in delegate mode (Shift+Tab). Coordinate teammates, never implement code directly. Spawn teammates for all SC execution.
Step 1: Plan Detection & SC Extraction
⚠️ CRITICAL: Always use absolute path based on Claude Code's initial working directory.
Full Implementation: See @REFERENCE.md - Step 1: Plan Detection (Full Bash)
Step 2.7: Pre-Execution Confidence
Purpose: Evaluate confidence before complex SCs. If < 0.5 → consult GPT Architect (rubric: @.claude/skills/gpt-delegation/SKILL.md).
Full Implementation: See @REFERENCE.md - Step 2.7: Pre-Execution Confidence (Full Bash)
Step 3: Execute with Ralph Loop (Per-SC Agent Selection)
Dependency Analysis, File Extraction & Agent Selection (supports both ### SC-N: and - [ ] **SC-N** formats):
What ships with it
1 file 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.
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.
- 5d ago First seen · 125 lines · 32 tokens per session scan A 15deaa77a7e5
execute-plan is a skill published in the GitHub repository changoo89/claude-pilot (20 stars, last pushed 6mo ago), licensed MIT. It adds 32 tokens to every session and 1,706 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
harness-diet
Measure and shrink the always-loaded context of a Claude Code harness (CLAUDE.md + rules without paths frontmatter) back under budget — migrate narrative to reference files, convert rules to path-scoped or skill-triggered loading, and verify zero governance loss with deterministic preservation checks. Use on "harness…
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
case-interview-practice
Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.
i18n-localization
Internationalization and localization for global applications. Use when adding multi-language support, handling regional formats, or preparing apps for global markets.
electron-desktop
Desktop application development with Electron for Windows, macOS, and Linux. Use when building cross-platform desktop apps, implementing native OS features, or packaging web apps for desktop.