agentmods.dev

myplan

A command that examines a task and writes an implementation plan to a PLAN file. It is the second stage of the embedeval workflow, which separates planning, implementation, review, and wrap-up.

In plain words
What is it for?
Use it to plan a task such as fixing CI or adding tests, while checking existing plans and listing the project's quality checks.
Why use it?
It creates a shared written plan with scope, affected files, and testing requirements before code is changed.

Command for Claude Code

11 26d ago A scan 0 tokens original Apache-2.0
View the source file Ecro/embedeval
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 commands/ecro/embedeval/myplan
Clone the repo
git clone --depth 1 https://github.com/Ecro/embedeval

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,072 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 $0.00000 $0.01072
Opus 5 $0.00000 $0.00536
Sonnet 5 $0.00000 $0.00214
Haiku 4.5 $0.00000 $0.00107

Measured yesterday against content hash 0c50fb420d62, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

myplan 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.

.claude/commands/myplan.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/myplan — Create implementation plan

Analyze, design, and write a PLAN document. Step 2 of the embedeval 5-stage workflow. The PLAN file is the only persistent artifact in this workflow — /execute, /review, and /wrapup all report to screen only.

Communication

  • Direct, evidence-based, no preamble.
  • Push back on unclear requirements before planning.
  • Lead with concerns; explain why you agree, not just "looks good."

Usage

/myplan <task-slug>

<task-slug> — short kebab-case identifier, e.g. context-quality-mode, fix-ci, negative-tests. Matches the filename plans/PLAN-<slug>.md.

Context

  • Repo: /home/noel/embedeval
  • PLAN destination: plans/PLAN-<slug>.md
  • Existing plans: plans/PLAN-*.md — browse first, avoid duplicating prior work
  • Embedeval quality gates (reference these in the PLAN's testing strategy):
    • uv run ruff format --check src/
    • uv run ruff check src/
    • uv run mypy src/
    • uv run pytest tests/
  • Doc auto-sync: uv run python scripts/sync_docs.py (mandatory before commit when cases/, src/, or tests/ changed)

Steps

  1. Clarify scope — confirm with user what's in and out of scope. If ambiguous, ask; don't guess.

  2. Prior work — grep plans/PLAN-*.md and CLAUDE.md "Learned Corrections" for related work. Read hits; note what to reuse or avoid repeating.

  3. Code review — Read affected modules under src/embedeval/ and existing tests. Understand current implementation before designing changes.

  4. Design — for non-trivial work, identify 2–3 approaches. Pick one with explicit rationale and rejected alternatives.

  5. Write the PLAN file — plans/PLAN-<slug>.md, using the template below.

PLAN template

---
type: plan
task_slug: <slug>
status: planning
created: YYYY-MM-DD
tags: [embedeval, plan, <topic>, <tech>]
---

# PLAN: <Title>

**Task:** <one-line description>
**Created:** <YYYY-MM-DD>

## Executive summary

**TL;DR:** <one sentence>.

### What
<2–3 sentences: the core change>

### Why
<1–2 sentences: motivation>

### Key decisions
- **<Decision>:** <what> — because <reason>

### Impact
- Complexity: Low | Medium | High
- Risk: Low | Medium | High
- Files changed: ~N
- Estimated effort: X hours

## Prior work

<Related PLAN-*.md, CLAUDE.md corrections, existing patterns — with file paths.>

## Problem analysis

### Current state
<What the code does today, with file:line references.>

### Success criteria
- [ ] <criterion 1>
- [ ] <criterion 2>

## Design

### Approach
<Chosen approach and rationale.>

### Alternatives considered
- **<Alt 1>:** <why rejected>

### Affected files
- `<path>` — <what changes>

## Implementation phases

### Phase 1: <name>
- [ ] <step>

### Phase 2: <name>
- [ ] <step>

## Testing strategy

- Unit tests: <what to add under tests/>
- Integration: <any end-to-end runs needed>
- Quality gates: `ruff format --check src/`, `ruff check src/`, `mypy src/`, `pytest tests/`
- Doc sync: run `scripts/sync_docs.py` if `cases/`/`src/`/`tests/` changed

## Risks

| Risk | Impact | Mitigation |
|------|--------|------------|
| <risk> | High/Med/Low | <how> |

## Review checklist (verify before /execute)

- [ ] Scope correct — nothing missing or unnecessary
- [ ] Design sound — no obvious flaws
- [ ] Affected-files list complete
- [ ] Tests cover every success criterion
- [ ] Risks identified with mitigations

Read the full file on GitHub · 160 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. yesterday First seen · 160 lines · 0 tokens per session scan A 0c50fb420d62

Subscribe to this mod's changes

myplan is a command published in the GitHub repository Ecro/embedeval (11 stars, last pushed 26d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,072 tokens. 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.

Code reviewDevOps and cloudTesting
Related

Other commands, from other repositories

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

clarify

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens

converge

Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.

github/spec-kit · 35 tokens

implement

Execute the implementation plan by processing and executing all tasks defined in tasks.md.

github/spec-kit · 14 tokens