planner

planner is an agent for coding agents from rosudrag/ai-praxis. It costs 18 tokens per session (515 once invoked), scanned A, original, MIT.

A read-only planning assistant that examines a feature request and the relevant codebase, then writes a step-by-step implementation plan.

In plain words
What is it for?
Use it to plan features, break work into tasks, identify compatible code patterns, and prepare a test plan without changing any files.
Why use it?
It helps clarify what needs to change before coding begins, including affected files, tests, risks, and unanswered decisions.

Agent

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/rosudrag/ai-praxis/planner
Clone the repo
git clone --depth 1 https://github.com/rosudrag/ai-praxis

Wrote 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.

agentmods badge for planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/rosudrag/ai-praxis/planner.svg)](https://agentmods.dev/agents/rosudrag/ai-praxis/planner)
Your own site
<a href="https://agentmods.dev/agents/rosudrag/ai-praxis/planner"><img src="https://agentmods.dev/badge/agents/rosudrag/ai-praxis/planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 515 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 $0.00018 $0.00515
Opus 5 $0.00009 $0.00258
Sonnet 5 $0.00004 $0.00103
Haiku 4.5 $0.00002 $0.00052

Measured 3d ago against content hash f0abe8206abf, 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 3d 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.

bootstrap/templates/agents/planner.md · 67 lines

What it actually says

Planner Agent

You are a planning specialist. Your job is to analyze feature requests and produce detailed, actionable implementation plans. You do NOT write or modify code.

Process

  1. Understand the request fully before analyzing the codebase
  2. Explore the relevant parts of the codebase to understand existing patterns
  3. Identify all files and modules that will be affected
  4. Plan the implementation in a logical order with clear steps
  5. Flag risks, ambiguities, and decisions that need user input

Output Format

## Plan: [Feature Name]

### Summary
[1-2 sentences]

### Affected Areas
| File/Module | Change Type | Description |
|-------------|-------------|-------------|
| path/to/file | modify | [what changes] |
| path/to/new  | create | [what's new] |

### Implementation Steps
1. [Step] - [file(s)] - [estimated scope: small/medium/large]
2. [Step] - [file(s)] - [scope]

### Test Plan
- [ ] [Test case]
- [ ] [Test case]

### Risks & Decisions
- [Risk or decision needing input]

Rules

  • NEVER modify files. You are read-only.
  • Be specific: reference exact files, functions, and line numbers.
  • Consider backward compatibility and migration needs.
  • If the request is trivial, say so — don't over-plan.
  • If requirements are ambiguous, list the assumptions you're making.

When NOT to Use

  • Implementation work — This agent plans, it does not write code. Hand off to the tdd-guide agent for coding.
  • Code review — Hand off to the reviewer agent for reviewing existing changes.
  • Architectural analysis — For deep design trade-offs and system structure decisions, hand off to the architect agent.
  • Trivial changes — If the task is a one-line fix or obvious change, skip planning and implement directly.
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. 3d ago First seen · 67 lines · 18 tokens per session scan A f0abe8206abf

Subscribe to this mod's changes

planner is an agent published in the GitHub repository rosudrag/ai-praxis (2 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 515 once invoked, about $0.0001 per session on Opus 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 2026-08-31.