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 rijuvashisht/Magneto --skill plangit clone --depth 1 https://github.com/rijuvashisht/MagnetoWrote 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/rijuvashisht/magneto/plan)<a href="https://agentmods.dev/skills/rijuvashisht/magneto/plan"><img src="https://agentmods.dev/badge/skills/rijuvashisht/magneto/plan/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/rijuvashisht/magneto/plan"><img src="https://agentmods.dev/badge/skills/rijuvashisht/magneto/plan.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 | $0.00000 | $0.00834 |
| Opus 5.5 | $0.00000 | $0.00334 |
| Sonnet 5.5 | $0.00000 | $0.00167 |
| Haiku 4.5 | $0.00000 | $0.00083 |
Grade A, and why
plan 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/plan — Community-Scoped Planning with Cost-Aware LLM Routing
Role: Eng Manager + CEO
Inputs: design.md (from /think)
Outputs: plan.md
Next skill: /review (or /autoplan for full review pipeline)
Audit actions: plan.started, plan.scoped, plan.drafted
Why This Skill Exists
gstack's /plan-eng-review asks generic architecture questions. Magneto's /plan scopes the context to the graph communities that actually matter for this change, and picks the cheapest adequate LLM per plan section.
The Protocol
Step 1: Read predecessor artifacts
Require .magneto/sprints/<id>/design.md from /think. If missing, say:
"No design.md found. Run /think first, or pass a task description to skip."
Step 2: Scope the graph context
From design.md, extract:
- Mentioned god nodes
- Mentioned community IDs
- File paths hinted at
Then:
magneto graph communities # full community list
magneto query --community <N> # inspect affected communities
magneto graph neighbors <node-id> # impact analysis on god nodes
Build a "scope set" = { files in affected communities ∪ neighbors of touched god nodes ∪ memory patterns for similar changes }.
Emit audit: magneto audit add plan.scoped --payload '{"communities":[...],"fileCount":N}'.
Step 3: Draft the plan (use cheapest adequate model)
For each plan section, route to the right LLM:
| Section | Model Tier | Rationale |
|---|---|---|
| File list / rename list | local/cheap (Ollama) | Mechanical |
| Test list | local/cheap | Mechanical |
| API contract | medium (GPT-4o-mini, Haiku) | Structured |
| Architecture diagram | expensive (Claude Sonnet/Opus) | Creative |
| Migration strategy | expensive | Requires judgment |
| Rollback plan | medium | Template-based |
Use magneto run --runner <name> to invoke the chosen runner per section, or instruct the host agent to switch models.
Step 4: Write plan.md
Structure:
# Plan: <title>
**Sprint:** <id>
**Design:** ./design.md
**Scope communities:** <list with sizes>
**Touched god nodes:** <list>
## Overview
<2-3 sentence summary tying back to design.md's wedge>
## Architecture
<diagram or textual description>
<call out which existing patterns are reused from memory>
## Files to Modify
| File | Change | Lines (est.) | Community |
|---|---|---|---|
| ... | ... | ... | ... |
## Files to Create
| File | Purpose | Lines (est.) |
|---|---|---|
| ... | ... | ... |
## API Contract
<TypeScript interfaces or OpenAPI snippets>
## Test Plan
| Test | Type | Covers |
|---|---|---|
| ... | unit/integration/e2e | Design requirement |
## Migration / Rollback
<if schema or breaking change>
## Risks
<enumerated with mitigation>
## Open Questions for /review
<things that need reviewer judgment>
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 · 123 lines · 0 tokens per session scan A 2472b4468b37
plan is a skill published in the GitHub repository rijuvashisht/Magneto (6 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 834 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.
Other skills, from other repositories
expense-review-policy
Review invoices and contracts against accounts-payable policy before human approval.
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
image-generation
Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
new-app
Scaffold a new Atomic Agents project from scratch — create the directory, pyproject.toml, env file, first agent, and a runnable entry point. Use when the user asks to start a new atomic-agents project from scratch, says "scaffold" / "new project" / "start from zero", or runs /atomic-agents:new-app.
powerpoint
Create designed, editable PowerPoint .pptx presentations with PptxGenJS. Use when the user asks to create, generate, update, or inspect a deck, slide deck, presentation, or .pptx file.