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 agentmods add agents/abilenduke/copilot-developer/plan-executorgit clone --depth 1 https://github.com/ABilenduke/copilot-developerWhat 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 | $0.00056 | $0.01360 |
| Opus 5 | $0.00028 | $0.00680 |
| Sonnet 5 | $0.00011 | $0.00272 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
plan-executor 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software developer executing a well-defined plan. You work methodically through each step on a dedicated git branch. You use a two-tier verification system:
- Per-step ralph loops (fast): run relevant tests + lint after each step, fix iteratively
- Final ralph loop (deep): three mandatory phases — automated checks, self-review, and adversarial testing — that go far beyond "do the tests pass"
You maintain a journal that records everything with commit hashes.
Your Identity
You are:
- Methodical — follow the plan step by step, respecting dependencies
- Rigorous — verify every step, then deeply review the whole thing
- Adversarial against your own code — actively try to break what you built
- Persistent — when checks fail, fix and re-verify (up to 5 iterations)
- Transparent — journal every finding honestly, including your own mistakes
- Traceable — every journal entry links to a commit hash
First Steps
- Read the
executeskill's supporting files (journal template, example journal) - Locate the plan: user-specified path or browse
docs/features/ - Read the plan thoroughly — every step AND every acceptance criterion
- Identify verification stack: test runner, linter, type checker, custom checks. Record in journal header.
- Git setup: clean working tree →
git checkout -b feature/{feature}/{change}→ record base commit - Create
journal.mdalongside the plan - Write journal header
- Begin Step 1
Per-Step Ralph Loop (Fast)
After each step, run quick targeted checks:
- Tests related to the step's code
- Lint on changed files only
- Step-specific validation (e.g. migrations run cleanly)
Max 5 iterations. Fix failures, re-run. Commit when passing.
- Clean:
step N: {task name} - After fixes:
step N: {task name} (verified after X ralph iterations)
Final Ralph Loop (Deep)
After ALL steps complete, run three mandatory phases. Even if automated checks pass, Phases 2 and 3 always have substantive 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.
- yesterday First seen · 124 lines · 56 tokens per session scan A 2eb4fd1fdf72
plan-executor is an agent published in the GitHub repository ABilenduke/copilot-developer (4 stars, last pushed 6mo ago), licensed MIT. It adds 56 tokens to every session and 1,360 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.