execute-plan

A command for carrying out an agreed coding plan in small batches, with a review after each batch. It uses TDD, or test-driven development: write a failing test, add the minimum code to pass it, then clean up.

In plain words
What is it for?
Use it to implement a feature or design that has already been planned. It helps organize implementation, testing, code review, progress updates, and the final summary.
Why use it?
It prevents a long, unchecked coding run from growing beyond the agreed scope. Regular reviews catch problems before the next batch begins.

Command for Claude Code

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 commands/webhook-co/webhook/execute-plan
Clone the repo
git clone --depth 1 https://github.com/webhook-co/webhook

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 439 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.00439
Opus 5 $0.00000 $0.00219
Sonnet 5 $0.00000 $0.00088
Haiku 4.5 $0.00000 $0.00044

Measured yesterday against content hash db5ec31d9ff5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

.claude/commands/execute-plan.md · 29 lines

What it actually says

/execute-plan

Implement an agreed plan in reviewed batches, not one giant uninterrupted run. Use this after a plan exists (from /brainstorming, /feature-dev, or a written design).

How to run

  1. Confirm the plan. Restate the batches you'll implement and their order. If there's no clear plan yet, stop and ask for one (or run /brainstorming first). Don't improvise scope.
  2. Work one batch at a time. For each batch:
    • Implement it under TDD — failing test first, then the minimum code to pass, then refactor (see the test-driven-development skill).
    • Keep changes scoped to the batch; don't drift into unrelated edits.
  3. Review checkpoint after each batch. Hand the diff to the code-reviewer agent (and the qa-test-reviewer agent when behavior on a correctness-critical path changed — signing/verification, dedup, retries, ordering, replay, metering). Address must-fix findings before moving on.
  4. Pause for me at each checkpoint with a one-line status: what landed, what the review said, and what's next. Don't barrel through all batches silently.
  5. Summarize at the end: what changed, test status, follow-ups, and anything needing human verification.

Hard rules

  • Never bypass the gate. No git commit --no-verify / git push --no-verify, no .only/.skip/ disabled tests, no lowered coverage thresholds. If the pre-commit/lint-staged hook fails, fix the root cause and make a new commit — CI required checks are the real gate and have no bypass.
  • Human-UI-testing hard stop. If a batch needs human visual/interaction/copy verification, stop and flag it for human testing; don't mark it done on your own.
  • Keep CLI/API/web/MCP at parity; reuse shared/ types. Stay public-safe (no pricing/account IDs).
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. yesterday First seen · 29 lines · 0 tokens per session scan A db5ec31d9ff5

Subscribe to this mod's changes

execute-plan is a command published in the GitHub repository webhook-co/webhook (0 stars, last pushed 6d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 439 tokens. 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.