executing-plans

executing-plans is a skill for Claude Code from boparaiamrit/skills-by-amrit. It costs 31 tokens per session (3,118 once invoked), scanned A, original, MIT.

A workflow for carrying out a detailed implementation plan one task at a time, with checks and small commits.

In plain words
What is it for?
It is for executing multi-step development plans, handling deviations, checking completion criteria, and committing each finished task.
Why use it?
It helps keep planned work on track and makes deviations, incomplete tasks, and failed verification steps visible.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skills-by-amrit plugin — 33 skills, 34 commands, 9 agents shipped together

Good fit It is for executing multi-step development plans, handling deviations, checking completion criteria, and committing each finished task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/boparaiamrit/skills-by-amrit/executing-plans
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.

Any agent
npx skills add boparaiamrit/skills-by-amrit --skill executing-plans
Clone the repo
git clone --depth 1 https://github.com/boparaiamrit/skills-by-amrit

Made for: Claude Code.

Or install skills-by-amrit, the plugin that ships this one along with the rest of its 33 skills, 34 commands, 9 agents.

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/boparaiamrit/skills-by-amrit/executing-plans/github.svg)](https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/executing-plans)
Your own site
<a href="https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/executing-plans"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/executing-plans/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.

agentmods 80×15 button for executing-plans

Your own site · 80×15
<a href="https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/executing-plans"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/executing-plans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,118 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.03118
Opus 5 $0.00015 $0.01559
Sonnet 5 $0.00006 $0.00624
Haiku 4.5 $0.00003 $0.00312

Measured 8d ago against content hash 091c550568b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 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.

skills/executing-plans/SKILL.md · 395 lines

How it starts

The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Executing Plans

Overview

Execute implementation plans task by task. Each task gets full attention, fresh context, complete verification, and its own atomic commit. The executor follows the plan as a contract — deviations require explicit approval.

Core principle: Plans are prompts. Follow them literally. Deviate only with permission.

The Iron Laws

1. NO TASK IS COMPLETE UNTIL ALL <done> CRITERIA ARE MET
2. NO DEVIATION FROM PLAN WITHOUT EXPLICIT APPROVAL
3. NO MOVING FORWARD WHEN CONTEXT USAGE > 70% — CHECKPOINT AND HAND OFF
4. NO SKIPPING <verify> — run the command, read the output, confirm the criteria

Context Engineering (CRITICAL)

You WILL experience quality degradation during long execution sessions. Plan for it.

Context Usage Action
0-30% Work normally — thorough, comprehensive
30-50% Still good — maintain quality
50-70% ⚠️ Warning zone — consider checkpointing after current task
70%+ 🛑 STOP — checkpoint immediately, do NOT start new tasks

Self-check: If you notice yourself:

  • Skipping verification steps → STOP, you're degrading
  • Writing shorter commit messages → STOP, you're degrading
  • Saying "this should work" instead of running tests → STOP, you're degrading

When to Use

  • After writing-plans produces a plan
  • When given an existing implementation plan with task anatomy
  • When a task list needs methodical execution

When NOT to Use

  • No plan exists yet (use brainstormingwriting-plans first)
  • Single-step bug fix (use systematic-debugging directly)
  • Exploratory work (use brainstorming first)

Anti-Shortcut Rules

YOU CANNOT:
- Execute multiple tasks before committing — one task, one commit
- Say "this task is done" without running ALL <verify> commands — run them, read output
- Skip writing the failing test — RED before GREEN, always
- Move to next task when current has warnings — clean is the standard
- Batch similar tasks "for efficiency" — each task gets its own cycle
- Modify the plan without approval — deviations require the Deviation Protocol
- Skip checkpoints — every 3 tasks, MANDATORY full-suite checkpoint
- Commit untested code — tests pass or it doesn't ship
- Say "close enough" — either it meets <done> criteria or it doesn't
- Continue past 70% context usage — checkpoint and hand off
- Ignore DON'T/AVOID instructions in <action> — they exist because someone hit that bug before

Read the full file on GitHub · 395 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. 8d ago First seen · 395 lines · 31 tokens per session scan A 091c550568b2

Subscribe to this mod's changes

executing-plans is a skill published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 3,118 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 2026-09-03.