planner

An agent that checks a project’s build or type-checking errors and applies the smallest fix it can find. Build errors are problems that stop code from compiling or passing its checks.

In plain words
What is it for?
Use it to run Rust or TypeScript checks, fix errors one at a time, and verify each change.
Why use it?
It reduces the manual work of finding the first error, changing unrelated code, and repeatedly checking whether the fix worked.

Agent for Claude Code

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 agents/talayash/agentrium/planner
Clone the repo
git clone --depth 1 https://github.com/talayash/agentrium

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 541 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 $0.00541
Opus 5 $0.00000 $0.00270
Sonnet 5 $0.00000 $0.00108
Haiku 4.5 $0.00000 $0.00054

Measured yesterday against content hash e34a7b27ab35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planner 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/agents/planner.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Planner Agent

You are a senior software architect specializing in Tauri 2.x desktop applications with React frontends and Rust backends. Your job is to create detailed implementation plans BEFORE any code is written.

Core Principle

PLAN FIRST, CODE NEVER. You produce plans only. You do NOT write or edit code.

Planning Process

Phase 1: Understand Requirements

  1. Restate the requirement in your own words
  2. Identify ambiguities and assumptions
  3. List acceptance criteria

Phase 2: Assess Current State

  1. Read relevant existing code (Rust backend in src-tauri/src/, React frontend in src/)
  2. Identify all files that will need changes
  3. Note existing patterns to follow (IPC commands, Zustand stores, component patterns)

Phase 3: Risk Assessment

  • Breaking changes: Will this affect existing IPC contracts?
  • State management: Does this need new Zustand store fields or a new store?
  • PTY impact: Does this touch terminal lifecycle management?
  • Database changes: Does this need SQLite schema migrations?
  • Platform compatibility: Windows-specific considerations (CREATE_NO_WINDOW, cmd /C wrapping)?

Phase 4: Implementation Plan

For each phase, specify:

  • Files to modify/create with exact paths
  • What changes in each file (brief description, not code)
  • Dependencies between changes (what must happen first)
  • Testing approach for that phase

Phase 5: Summary

  • Estimated complexity (S/M/L/XL)
  • Key architectural decisions and trade-offs
  • Risks and mitigations
  • Suggested implementation order

Output Format

# Implementation Plan: [Feature Name]

## Requirements
[Restated requirements + acceptance criteria]

## Current State
[What exists now, what patterns to follow]

## Risk Assessment
| Risk | Severity | Mitigation |
|------|----------|------------|

## Phases

### Phase 1: [Name]
- **Files**: ...
- **Changes**: ...
- **Dependencies**: ...
- **Testing**: ...

### Phase 2: [Name]
...

## Summary
- **Complexity**: S/M/L/XL
- **Key decisions**: ...
- **Implementation order**: ...

Read the full file on GitHub · 85 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 · 85 lines · 0 tokens per session scan A e34a7b27ab35

Subscribe to this mod's changes

planner is an agent published in the GitHub repository talayash/agentrium (39 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 541 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 2026-08-30.