Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ckorhonen/claude-skillsnpx agentmods add skills/ckorhonen/claude-skills/executing-plansWrote 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/ckorhonen/claude-skills/executing-plans)<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/executing-plans"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/executing-plans.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 | $0.00057 | $0.01555 |
| Opus 5 | $0.00028 | $0.00777 |
| Sonnet 5 | $0.00011 | $0.00311 |
| Haiku 4.5 | $0.00006 | $0.00155 |
Grade A, and why
executing-plans 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 8d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Executing Plans
Overview
Load plan, review critically, execute tasks in batches, report for review between batches.
Core principle: Batch execution with checkpoints for architect review.
Announce at start: "I'm using the executing-plans skill to implement this plan."
The Process
Step 1: Load and Review Plan
- Read the plan file completely
- Review it critically — this is where you catch flaws before they become expensive rework. Look for:
- Steps that seem vague or contradictory
- Missing dependencies or setup
- Assumptions that don't hold in your actual codebase
- Technical choices you'd question
- If concerns exist: Raise them with your partner before proceeding. Getting alignment now saves many hours of wrong execution
- If the plan looks solid: Create a todo tracker and proceed to Step 2
Step 2: Execute Batch
Default: First 3 tasks per batch
The checkpoint-driven approach (3 tasks, pause for feedback, continue) gives your partner visibility and prevents you from building on a flawed foundation.
For each task in the batch:
- Mark it as in_progress in your tracker
- Follow the plan's steps exactly — they're designed to be small and verifiable
- Run the specified verifications before marking done — this catches mistakes early
- If verification fails: stop, report it, and wait for guidance
- If verification passes: mark as completed and move to the next task
Keep focus tight. Executing 3 tasks well and getting feedback is faster than executing 10 tasks blind and discovering you went the wrong direction halfway through.
Step 3: Report
When the batch is done, report clearly:
- Show what was implemented (what changed, new files, modified code)
- Show verification output (test results, error messages if any)
- Summarize any unexpected findings or minor deviations from the plan
- End with: "Ready for feedback."
This pause-to-report is critical. It gives your partner a chance to course-correct before you invest more work.
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.
- 8d ago First seen · 137 lines · 57 tokens per session scan A fe4a65a49fe1
executing-plans is a skill published in the GitHub repository ckorhonen/claude-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 1,555 once invoked, about $0.0003 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.