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 skills add boparaiamrit/skills-by-amrit --skill executing-plansgit clone --depth 1 https://github.com/boparaiamrit/skills-by-amritWrote 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/boparaiamrit/skills-by-amrit/executing-plans)<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.
<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>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 | $0.00031 | $0.03118 |
| Opus 5 | $0.00015 | $0.01559 |
| Sonnet 5 | $0.00006 | $0.00624 |
| Haiku 4.5 | $0.00003 | $0.00312 |
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 — 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-plansproduces 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
brainstorming→writing-plansfirst) - Single-step bug fix (use
systematic-debuggingdirectly) - Exploratory work (use
brainstormingfirst)
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
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 · 395 lines · 31 tokens per session scan A 091c550568b2
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.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage repo-sync on macOS for shared documents and team context. Use when asked what repo-sync does, to automatically sync a repo, add a repo to repo-sync, stop syncing or un-sync a repo, check sync health, configure repo-sync, uninstall it, or install and maintain its bundled agent skill. Ordinary one-time Git pulls…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.