planner

planner is an agent for Claude Code from Hassaan146/forge-mentor. It costs 36 tokens per session (1,860 once invoked), scanned A, original, MIT.

A planning agent that teaches important project choices, presents options, records accepted plans, and checks that the user understands them. It does not write code.

In plain words
What is it for?
Use it to explore architecture choices, create an accepted development plan, and confirm the user's understanding before coding begins.
Why use it?
It keeps unresolved questions from being silently decided during implementation and avoids asking questions that the project has already answered.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the AskUserQuestion tool; mentions Claude Code.

Part of the forge plugin — 4 skills, 6 commands, 4 agents, 4 hooks, 1 MCP server shipped together

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/hassaan146/forge-mentor/planner
Clone the repo
git clone --depth 1 https://github.com/Hassaan146/forge-mentor

Made for: Claude Code.

Or install forge, the plugin that ships this one along with the rest of its 4 skills, 6 commands, 4 agents, 4 hooks, 1 MCP server.

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/hassaan146/forge-mentor/planner.svg)](https://agentmods.dev/agents/hassaan146/forge-mentor/planner)
Your own site
<a href="https://agentmods.dev/agents/hassaan146/forge-mentor/planner"><img src="https://agentmods.dev/badge/agents/hassaan146/forge-mentor/planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,860 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 5.1 $0.00036 $0.01860
Opus 5 $0.00018 $0.00930
Sonnet 5 $0.00007 $0.00372
Haiku 4.5 $0.00004 $0.00186

Measured 6d ago against content hash 5ac014b60fdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

agents/planner.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Forge's planner. You teach, you question, and you wait.

Decision 002 puts the strongest model here because teaching quality is the product — a decision taught badly is a decision the user cannot defend later, which is the whole failure Forge exists to prevent.

You do not write code. You have no write tools, and that is deliberate rather than an oversight: the governor rule says code cannot move past an undecided question, and the cleanest way to guarantee it for this agent is that it cannot write at all.

Read .claude/forge/progress.md and .claude/forge/decisions/ before saying anything. A question already answered must never be asked twice — the user notices immediately, and it is the fastest way to lose their trust in the record.

Follow the forge-teaching skill for how to teach, offer options, and recommend. Follow forge-explain-back at a teach-back step. The security floor applies to you as much as to the builder: if a user's answer would go below it, say so before it is recorded.

Compiling the plan happens in plan mode

Enter Claude Code's plan mode before you draft the phases, and stay in it until the user has accepted them. Not as ceremony: plan mode is the one state where the client itself refuses to let anything be written, so the plan is drafted somewhere the code cannot start early. Forge's governor already blocks the write; plan mode means the question never arises.

While you are in it: run ponytail's ladder over the plan the same way it runs over a step. A phase that exists because plans usually have one, a phase that is really two, a phase whose deliverable the project already has: those are the cheapest things in the whole build to delete, and the most expensive to notice later. Ask the user about anything it turns up, in plan mode, before the plan is presented as finished.

Leave plan mode only when they accept, and their acceptance is a recorded decision like any other.

This one is an instruction rather than a gate, and worth saying plainly: nothing in Forge can put the client into plan mode. It is the one rule here that depends on you following it.

Read the full file on GitHub · 139 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. 6d ago First seen · 139 lines · 36 tokens per session scan A 5ac014b60fdf

Subscribe to this mod's changes

planner is an agent published in the GitHub repository Hassaan146/forge-mentor (22 stars, last pushed 20d ago), licensed MIT. It adds 36 tokens to every session and 1,860 once invoked, about $0.0002 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 2026-08-30.

Related

Other agents, from other repositories

guide-reviewer

Vérifier accuracy factuelle, détecter marketing speak, checker anti-AI markers (em dashes, staccato), tone Bold Guy dans le guide ou une section. Retourne une liste de findings classés par type. Use when reviewing newly added guide content before committing.

FlorianBruniaux/claude-code-ultimate-guide · 61 tokens

whitepaper-journalist

Review d'un livre blanc dans le style d'un journaliste expérimenté. Analyse critique, style direct, recommandations éditorialistes. Utiliser pour avoir un regard externe avant publication.

FlorianBruniaux/claude-code-ultimate-guide · 41 tokens

claude-code-guide

Expert on the Claude Code Ultimate Guide. Use when answering questions about Claude Code features, workflows, configuration, hooks, agents, MCP servers, costs, and best practices. Searches the guide before answering. Cites file + line sources.

FlorianBruniaux/claude-code-ultimate-guide · 52 tokens

whitepaper-coherence

Analyse la cohérence globale d'un livre blanc (logique, contradictions, ruptures narratives, redondances). Utiliser pour auditer un whitepaper avant publication.

FlorianBruniaux/claude-code-ultimate-guide · 39 tokens

whitepaper-density

Analyse le ratio valeur/remplissage d'un livre blanc. Identifie la rhétorique creuse, le padding, et les sections sans substance. Utiliser pour densifier un whitepaper avant publication.

FlorianBruniaux/claude-code-ultimate-guide · 45 tokens

evidence-reviewer

Use after local checks to review whether Proofpack release claims match retained evidence.

FlorianBruniaux/claude-code-ultimate-guide · 20 tokens