A command that writes a detailed, multi-file work plan for another coding agent to follow. The plan is saved in a dated folder under docs/plans/.

Use it to investigate a non-trivial task and produce an overview, separate plans for each work area, and a status tracker.

It turns a broad request into a recorded set of files, owners, tests, and implementation areas before anyone changes code.

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/universal-lsp/planx

Clone the repo

git clone --depth 1 https://github.com/developerz-ai/universal-lsp

Made for: Claude Code.

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 536 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.

Model	Per session	Once invoked
Fable 5	$0.00028	$0.00536
Opus 5	$0.00014	$0.00268
Sonnet 5	$0.00006	$0.00107
Haiku 4.5	$0.00003	$0.00054

Measured yesterday against content hash 78822a938cb6, 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 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/commands/planx.md · 44 lines

What it actually says

/planx

Plan only. No implementation, no builds, no edits outside the plan dir.

Goal

$ARGUMENTS

Steps

Resolve the path. date +%Y %m %d. Dir = docs/plans/<YYYY>/<MM>/<DD>/. Glob docs/plans/<YYYY>/<MM>/<DD>/1* → next = highest 1NN-* + 1, else 101. Slug kebab-case, ≤ 5 words.
Explore read-only (Task, subagent_type=Explore, "very thorough"): the files to touch with file:line, which subsystem owns them (graph-lite / engine / analysis / plugins), the existing tests and how they are registered (ulsp_add_test), and anything in docs/research/things-to-know.md or docs/gotchas.md that already covers this ground. Skip only for trivial asks.
Write overview.md plus one <NN>-<aspect>.md per separable area of work. Never a single plan.md. Split by area, not by chapter: the slice boundary is the file-set boundary an executor locks on, and the file set is the PR. Shapes and rules: docs/plans/README.md.
Write status.yml — the one tracker. created_by/owner from git config user.name; leave worked_by: "" so another agent can claim it.

Rules

Compact English. Fragments. Tables. file:line and Class::method over prose.
Reference, never paste. Pasted code is stale on arrival.
No checkboxes in the .md slices — status.yml is the only tracker.
Assume CLAUDE.md; do not restate it.
If a slice touches graph-lite/, say explicitly which vocabulary the executor may not use — that guard fires late otherwise.

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.

yesterday First seen · 44 lines · 28 tokens per session scan A 78822a938cb6

Subscribe to this mod's changes

planx is a command published in the GitHub repository developerz-ai/universal-lsp (0 stars, last pushed 11d ago), licensed Apache-2.0. It adds 28 tokens to every session and 536 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.

Planning ai-agents cmake code-intelligence code-navigation cpp20

rb-setup

First-time setup. Configure the LLM API key, or a no-API-key local host runner (Codex / Trae / Claude / any headless CLI) that RepoBrain uses for codebase Q&A and refresh. / 首次 setup，配置 RepoBrain 代码问答与 refresh 所需的 LLM API key，或无需 API key 的本地 host runner（Codex / Trae / Claude / 任意无头 CLI）。.

study8677/repobrain · 92 tokens

planx