A command that creates a dated folder containing a concise, self-contained plan for another AI to implement.

Use it to inspect a codebase, identify files and tests involved, and save numbered plans under docs/plans/.

It turns a task request into a consistent implementation plan and keeps planning separate from code changes.

planx — Command by developerz-ai

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 commands/developerz-ai/ai-task-master/planx

Clone the repo

git clone --depth 1 https://github.com/developerz-ai/ai-task-master

Made for: Claude Code.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,780 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.00030	$0.01780
Opus 5	$0.00015	$0.00890
Sonnet 5	$0.00006	$0.00356
Haiku 4.5	$0.00003	$0.00178

Measured 2d ago against content hash 472e141efbd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planx scanned grade A with 1 finding 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 2d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Portability: code runs unchanged on Bun, Node ≥20, Deno ≥1.40. No `Bun.file`/`Bun.$`/`Bun.spawn` in shipped code (use `node:fs/promises`, `node:child_process`/`execa`, web `fetch`). Bun-only APIs are a portability bug.

.claude/commands/planx.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/planx

Produce a concise plan another AI can execute with zero extra context. Plan only — no implementation, no code execution, no edits outside the plan dir.

Goal

$ARGUMENTS

Steps

Resolve path. Run date +%Y, date +%m, date +%d. Dir = docs/plans/<YYYY>/<MM>/<DD>/. Glob docs/plans/<YYYY>/<MM>/<DD>/1* → next number = highest existing 1NN-* + 1, else 101. Slug = kebab-case title, max 5 words. Final plan dir: docs/plans/<YYYY>/<MM>/<DD>/<1NN>-<slug>/.
Explore. Task (subagent_type=Explore, thoroughness="very thorough"): existing patterns + files to touch (file:line), the right workspace (packages/aitm for aitm, packages/ai-claude-compat for the AI-SDK/Claude-compat layer), the module(s) under packages/aitm/src/<module>/ from the module map (Credentials, AgentConfigDetector, StateStore, Planner, Worker, Reviewer, GitHubClient, WorkLoop, CLI, Logger), tests (unit *.test.ts paired with the module vs integration in packages/aitm/test/integration/), provider wiring in Credentials, gotchas. Prefer codegraph_* for structural lookups. Skip only for trivial asks.
Write the plan as multiple files in the plan dir — never one big plan.md. Always produce an overview.md index plus one <NN>-<aspect>.md per separable area (e.g. 01-module.md, 02-subagent.md, 03-cli.md, 04-tests.md). Split by area of work so each file is independently executable and stays short. Match the existing house style in docs/plans/ — terse fragments, file:line refs, tables.

overview.md — the map. Sections:

# <Title>

## Goal
1-2 sentences: what + why.

## Context
- Stack facts the executor needs (Bun dev runtime; must run unchanged on Bun + Node ≥20 + Deno ≥1.40; ESM only; `ai` package with `ToolLoopAgent` + subagents-as-tools; OpenRouter-only inference via `Credentials`; `gh` CLI wrapper — only what's relevant).
- Reference patterns: `packages/aitm/src/<module>/<file>.ts:12` — follow this for Z.

## Plan files (execute in order)
1. [`01-<aspect>.md`](01-<aspect>.md) — one line: what it covers.
2. [`02-<aspect>.md`](02-<aspect>.md) — ...

## Done when
- Verifiable acceptance criteria spanning the whole feature.

## Risks / open questions
- Anything the executor must decide or watch.

Read the full file on GitHub · 106 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.

2d ago First seen · 106 lines · 30 tokens per session scan A 472e141efbd7

Subscribe to this mod's changes

planx is a command published in the GitHub repository developerz-ai/ai-task-master (5 stars, last pushed 26d ago), licensed MIT. It adds 30 tokens to every session and 1,780 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review Data and AI LLM Testing ai-agent autonomous-agent bun cli github-automation

upgrade-webkit

Upgrade Bun's WebKit fork to the latest upstream version of WebKit.

oven-sh/bun · 14 tokens

dedupe

Find duplicate GitHub issues.

oven-sh/bun · 5 tokens

ashlr-dashboard

Rich token-savings dashboard — per-tool bar charts, 7d/30d sparklines, projected annual savings, and cost in dollars.

ashlrai/ashlr-plugin · 34 tokens

scriptwriter-draw

Draw a random chaos card from the 13-card deck — a plot-twist prompt the user can use as a scene seed, a basistext for an RRR cascade, or a riff for a room contribution.

cambridgetcg/agenttool · 43 tokens

specsync-create-spec

Create a new spec-sync module spec.

CorvidLabs/agent-3md · 0 tokens

nimbus-embedding-routing

Hybrid 384/1536-dim embedding routing (Phase 5 T6 PR 3): PROSEHEAVYTYPES, EMBEDDINGDIMLOCAL/EMBEDDINGDIMOPENAI, the RoutingEmbeddingPipeline wrapper, dual-table search (vecitems384 + vecitems1536 via vectorSearchChunksDual), the V30 migration (1536-dim table + dim-aware delete triggers), the nimbus index reembed CLI +…

nimbus-agent/Nimbus · 218 tokens

planx