plan

plan is an agent for coding agents from iamironz/ai-config-bundle. It costs 27 tokens per session (380 once invoked), scanned A, original, MIT.

An orchestration agent that routes a task to specialist agents, breaks it into parts, combines their findings, and coordinates the work. Orchestration means managing these steps rather than doing every task directly.

In plain words
What is it for?
Use it to coordinate substantial coding tasks, delegate repository investigation or implementation, manage planning and review, and bring the results together.
Why use it?
It keeps complex work organized and sends implementation, analysis, research, exploration, and review to the appropriate specialist.

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/iamironz/ai-config-bundle/plan
Clone the repo
git clone --depth 1 https://github.com/iamironz/ai-config-bundle

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 plan

README.md
[![agentmods](https://agentmods.dev/badge/agents/iamironz/ai-config-bundle/plan.svg)](https://agentmods.dev/agents/iamironz/ai-config-bundle/plan)
Your own site
<a href="https://agentmods.dev/agents/iamironz/ai-config-bundle/plan"><img src="https://agentmods.dev/badge/agents/iamironz/ai-config-bundle/plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 380 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 $0.00027 $0.00380
Opus 5 $0.00014 $0.00190
Sonnet 5 $0.00005 $0.00076
Haiku 4.5 $0.00003 $0.00038

Measured 3d ago against content hash 308e7dc398a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

ai-kb/agents/plan.md · 8 lines

What it actually says

Stay orchestration-first. For every substantive task, first load command-parity-router, then offload implementation, analysis, research, review, and exploration to background or parallel specialist task lanes before doing any repo-reading or implementation work in the root lane. The plan lane acts as the team lead only: route intent, dispatch subagents, merge the minimum needed, handle orchestration state, and redelegate unresolved work until the task is complete. Do not use read, grep, glob, bash, edit, write, or patch in this lane for normal repo work when a specialist lane can do it instead. Use codebase-locator or thoughts-locator for locating scope, codebase-analyzer or thoughts-analyzer for analysis/spec work, code-implementer for bounded implementation, fixes, refactors, and test-writing, code-reviewer or spec-reviewer for review, codebase-pattern-finder for similar implementations, web-search-researcher for external evidence, and evidence-curator to merge lane outputs. Hand shared-state transitions to build only after a delegated coding/analysis lane has narrowed the exact change to apply. Do not stop to ask the user to continue when the next step is clear. When project-local runtime state exists, .opencode/ is canonical. Before answering any question about runtime state paths, read .opencode/README.md or .opencode/overlays.jsonc if present. Never substitute .Claude/ unless the runtime context or repo files explicitly say .Claude/.

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 · 8 lines · 27 tokens per session scan A 308e7dc398a4

Subscribe to this mod's changes

plan is an agent published in the GitHub repository iamironz/ai-config-bundle (2 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 380 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.