Borrowing it
Nothing to install: this file belongs to cognitx-leyton/codegraph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cognitx-leyton/codegraph/main/.claude/commands/plan_local.mdgit clone --depth 1 https://github.com/cognitx-leyton/codegraphWrote 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/commands/cognitx-leyton/codegraph/plan_local)<a href="https://agentmods.dev/commands/cognitx-leyton/codegraph/plan_local"><img src="https://agentmods.dev/badge/commands/cognitx-leyton/codegraph/plan_local/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/commands/cognitx-leyton/codegraph/plan_local"><img src="https://agentmods.dev/badge/commands/cognitx-leyton/codegraph/plan_local.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 | $0.00007 | $0.04819 |
| Opus 5.5 | $0.00003 | $0.01928 |
| Sonnet 5.5 | $0.00001 | $0.00964 |
| Haiku 4.5 | $0.00001 | $0.00482 |
Grade A, and why
plan_local 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 2mo 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 — 546 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Plan Generator
Input: $ARGUMENTS
Objective
Transform the input into a battle-tested implementation plan through codebase exploration, research, and pattern extraction.
Core Principle: PLAN ONLY - no code written. Create a context-rich document that enables one-pass implementation.
Order: CODEBASE FIRST → REUSE INVENTORY → RESEARCH IF NEEDED → DESIGN → GENERATE.
Phase 1: PARSE
Determine Input Type
| Input | Action |
|---|---|
.prd.md file |
Read PRD, extract next pending phase |
Other .md file |
Read and extract feature description |
| Free-form text | Use directly as feature input |
| Blank | Use conversation context |
Extract Feature Understanding
- Problem: What are we solving?
- User Story: As a [user], I want to [action], so that [benefit]
- Type: NEW_CAPABILITY / ENHANCEMENT / REFACTOR / BUG_FIX
- Complexity: LOW / MEDIUM / HIGH
Prior Plan Check
If other plans exist in .agents/plans/:
- Read their summaries to understand what infrastructure they create
- Note any shared files (e.g.,
ViewTypeSwitcher.tsxmodified by multiple plans) - Reference prior plans explicitly: "Depends on: {plan}.plan.md creating {component}"
- If a shared file will be modified by multiple plans, note the merge order
Phase 2: EXPLORE
Study the Codebase
Use the Explore agent to find:
- Similar implementations - analogous features with file:line references
- Naming conventions - actual examples from the codebase
- Error handling patterns - how errors are created and handled
- Type definitions - relevant interfaces and types
- Test patterns - test file structure and assertion styles
Document Patterns
| Category | File:Lines | Pattern |
|---|---|---|
| NAMING | path/to/file.ts:10-15 |
{pattern description} |
| ERRORS | path/to/file.ts:20-30 |
{pattern description} |
| TYPES | path/to/file.ts:1-10 |
{pattern description} |
| TESTS | path/to/test.ts:1-25 |
{pattern description} |
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.
- 2mo ago First seen · 546 lines · 7 tokens per session scan A 9035f7befbb5
plan_local is a command published in the GitHub repository cognitx-leyton/codegraph (12 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 4,819 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
feedback
A design-stage security review for product requirement documents and other planning documents; a PRD is a document describing what a product should do.
va
A read-only security review of a codebase across eight architecture areas, with findings checked against file-and-line evidence.
compliance
A follow-up security check that verifies whether earlier findings were fixed and, depending on the selected mode, looks for new problems.
pentest
A read-only penetration-testing command for examining source code from an attacker’s perspective and producing proof-of-concept checks. Penetration testing is authorized security testing that tries to verify exploitable weaknesses.
run
A security-workflow coordinator that turns a natural-language request into a plan involving code review, verification, attack testing, or reporting.
verify
An independent recheck of a security assessment report that derives conclusions from its own evidence instead of accepting the original findings.