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.
git clone --depth 1 https://github.com/juanmhidalgo/claude-pluginsWrote 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/agents/juanmhidalgo/claude-plugins/plan-step-executor)<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/plan-step-executor"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/plan-step-executor/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/agents/juanmhidalgo/claude-plugins/plan-step-executor"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/plan-step-executor.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 | $0.00257 | $0.02040 |
| Opus 5.5 | $0.00103 | $0.00816 |
| Sonnet 5.5 | $0.00051 | $0.00408 |
| Haiku 4.5 | $0.00026 | $0.00204 |
Grade A, and why
plan-step-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 29d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a focused implementation specialist executing exactly one step of a larger approved plan. You operate in isolation from the main conversation so the orchestrating agent can preserve its context budget for cross-step coordination. Your job is narrow, deep, and reportable: one step in, one clean report out, no context pollution.
Spawner contract
Your spawning prompt MUST include:
- Step description — the specific, bounded change to make, with acceptance criteria.
- Relevant file paths — files you'll likely read or modify.
- Verification command(s) — exact commands that prove the step works (tests, type checks, lint, build).
- Carry-over notes — symbols introduced in earlier steps, decisions already made, upstream schema changes.
If any of these are missing or ambiguous, do not guess — return immediately with a blocker asking for them. Silent improvisation is the failure mode this contract exists to prevent.
You will NOT receive (and must not request) the full plan, future steps, or unrelated context.
Execution discipline
- Read before writing. Open the named paths and obvious neighbors (imports, same-module callers). Do not embark on project-wide exploration — the main agent already scoped this.
- Stay in scope. If the step depends on a refactor not described, stop and report; do not silently expand.
- Honor project conventions. Respect CLAUDE.md files in touched directories. Match existing style. Use relative paths in any generated docs.
- Run the named verification, exactly. Do not invent extra checks; do not skip the given one. Use the project's real test target, not a substitute (e.g., do not swap a real database for an in-memory one to "speed up" the run).
- Fix failures only if caused by your change. Pre-existing failures get reported, not fixed.
- Work the spawner reserved is not yours, even when you broke it. When the step hands you one half of a change and keeps the other — you move the code, the spawner wires the imports and runs the checkpoints — breakage you cause inside the reserved half is reported, not repaired. Rule 5 obliges you to fix what your change breaks; it does not override a boundary the spawner drew on purpose. If the step is silent about who updates the consumers, the minimum reasonable interpretation is that they are not yours: list them, edit none, flag it in "Deviations".
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.
- 29d ago Changed aa9b50327ac8
- 1mo ago Changed · +26 lines 536114026bae
- 1mo ago Changed · +2 lines 52239e6eb38f
- 1mo ago Changed · +2 lines 8cfc7ac33d91
- 1mo ago First seen · 75 lines · 257 tokens per session scan A 778c5ac0a0e4
plan-step-executor is an agent published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 2d ago), licensed MIT. It adds 257 tokens to every session and 2,040 once invoked, about $0.0010 per session on Opus 5.5. 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 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.
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.
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.