executing-plans

executing-plans is a skill for Claude Code from MereWhiplash/engram-cogitator. It costs 35 tokens per session (1,457 once invoked), scanned A, original, MIT.

A process for implementing a written development plan one task at a time using TDD, or test-driven development: write a failing test, make it pass, then improve the code.

In plain words
What is it for?
Use it when a plan is in docs/plans and the work is on a feature branch; it loads project context, executes tasks, reviews the result, and finishes the branch.
Why use it?
It keeps implementation tied to the plan and requires each change to be checked before moving on.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; names the TodoWrite tool; mentions Codex.

Part of the cogitation plugin — 20 skills, 1 command, 1 hook shipped together

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/merewhiplash/engram-cogitator/executing-plans
Any agent
npx skills add MereWhiplash/engram-cogitator --skill executing-plans
Clone the repo
git clone --depth 1 https://github.com/MereWhiplash/engram-cogitator

Made for: Claude Code.

Or install cogitation, the plugin that ships this one along with the rest of its 20 skills, 1 command, 1 hook.

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.

agentmods badge for executing-plans

README.md
[![agentmods](https://agentmods.dev/badge/skills/merewhiplash/engram-cogitator/executing-plans.svg)](https://agentmods.dev/skills/merewhiplash/engram-cogitator/executing-plans)
Your own site
<a href="https://agentmods.dev/skills/merewhiplash/engram-cogitator/executing-plans"><img src="https://agentmods.dev/badge/skills/merewhiplash/engram-cogitator/executing-plans.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,457 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 5.1 $0.00035 $0.01457
Opus 5 $0.00017 $0.00728
Sonnet 5 $0.00007 $0.00291
Haiku 4.5 $0.00003 $0.00146

Measured 6d ago against content hash c74a60b76ee7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

cogitation/skills/executing-plans/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Executing Plans

Execute a plan continuously in TDD, then review.

Announce: "I'm using the executing-plans skill to implement this plan."

The Rule

Every task follows @tdd: RED → GREEN → REFACTOR
No production code without a failing test first.

Prerequisites

  • Plan exists in docs/plans/YYYY-MM-DD-<topic>.md
  • On a feature branch

The Flow

Verify Branch → EC Search → Load Plan → Execute Tasks → Review → Finish

Step 1: Verify Branch

git branch --show-current

Must be on a feature branch, not main.

Step 2: Load Context

Get project config and relevant context:

ec_search:
  query: project config
  type: config

ec_search:
  query: [feature area]
  type: pattern

ec_search:
  query: [feature area]
  type: learning

Note any gotchas or patterns that apply to this implementation.

Step 3: Load and Review Plan

  1. Read the plan file
  2. Choose ONE progress tracking approach (don't mix):
    • Tasks (preferred): If TaskCreate/TaskUpdate tools are available, use Tasks. Creates persistent, shareable progress.
    • TodoWrite (fallback): If Tasks aren't available, use TodoWrite for the session.
  3. If concerns about the plan, raise them before starting

Important: Pick one approach and stick with it for the entire execution. Don't mix Tasks and TodoWrite.

Option A: Using Tasks (Preferred)

If TaskCreate/TaskUpdate/TaskList tools are available, create one task per plan task:

TaskCreate: "Task 1: [first task summary]"
TaskCreate: "Task 2: [second task summary]" → addBlockedBy: [task 1 id]
... one per plan task, chained in order

Benefits:

  • Progress survives context switches and session restarts
  • Subagents can share the same task list with CLAUDE_CODE_TASK_LIST_ID
  • Dependencies prevent out-of-order execution

Option B: Using TodoWrite (Fallback)

If Tasks aren't available, create a TodoWrite with all plan tasks and update as you go.

Step 4: Execute the Plan

Execute continuously — work through every task in order, stopping only for a real blocker (see "When to Stop"). Do not pause for feedback between tasks; that round-trip adds latency without improving quality.

Read the full file on GitHub · 197 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.

  1. 6d ago First seen · 197 lines · 35 tokens per session scan A c74a60b76ee7

Subscribe to this mod's changes

executing-plans is a skill published in the GitHub repository MereWhiplash/engram-cogitator (4 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 1,457 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 2026-08-31.