planx

planx is a command for Claude Code from sebyx07/claude-code-bible. It costs 31 tokens per session (673 once invoked), scanned A, original, MIT.

A command that writes a detailed plan for a new documentation chapter without writing the chapter itself. It places the plan in a dated folder under docs/plans.

In plain words
What is it for?
Exploring nearby documentation, outlining sections, recording sources and links to update, and tracking the plan's status.
Why use it?
It separates research and structure from prose writing, so another AI can use a clear, self-contained blueprint.

Command for Claude Code

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/sebyx07/claude-code-bible/planx
Clone the repo
git clone --depth 1 https://github.com/sebyx07/claude-code-bible

Made for: Claude Code.

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 planx

README.md
[![agentmods](https://agentmods.dev/badge/commands/sebyx07/claude-code-bible/planx.svg)](https://agentmods.dev/commands/sebyx07/claude-code-bible/planx)
Your own site
<a href="https://agentmods.dev/commands/sebyx07/claude-code-bible/planx"><img src="https://agentmods.dev/badge/commands/sebyx07/claude-code-bible/planx.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 673 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 $0.00031 $0.00673
Opus 5 $0.00015 $0.00336
Sonnet 5 $0.00006 $0.00135
Haiku 4.5 $0.00003 $0.00067

Measured 4d ago against content hash da0e0215911b, 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 4d 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.

.claude/commands/planx.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/planx

Plan only — outline the writing, never write the chapter. No edits outside the plan dir; never touch docs/NN-*.md from here.

Goal

$ARGUMENTS

Steps

  1. Path. date +%Y/%m/%d. Glob docs/plans/<YYYY>/<MM>/<DD>/1* → next 1NN (else 101). Slug kebab-case, ≤5 words. Dir: docs/plans/<YYYY>/<MM>/<DD>/<1NN>-<slug>/.
  2. Explore. Task (Explore, "very thorough"): the adjacent chapters, the README TOC row that will change, every cross-link that must be added or updated (grep -rn "NN-"), and the ch. 11 rules the prose must obey.
  3. Write overview.md — Goal (what the chapter teaches, why it earns a slot) · Placement (chapter number, neighbours, TOC row text) · Section outline (one line per ##) · Plan files (numbered) · Done when · Risks.
  4. One <NN>-<aspect>.md per section or per file touched> Part of overview.md. Depends on: <NN or none>. · What to write (bullets, the claims to make) · Sources to verify against · Links to add/update (pathpath) · Done when. Never draft the prose here.
  5. status.yml alongside overview.mdplan, title, status (not_started|in_progress|blocked|complete|superseded), created_by/owner from git config user.name, worked_by: "", percent: 0, current_focus: "", slices: (one row per <NN> file with status/percent), evidence: [], notes: "", last_updated.

Rules

  • Compact English, fragments over sentences, tables for structured data — the plan obeys ch. 11 too.
  • Reference-only: point at chapters and line numbers, don't paste prose.
  • No checkboxes. status.yml is the only tracker.
  • Never plan around git worktrees. The writer works directly in this checkout; parallel agents share it, one chapter file each. Never isolation: worktree.
  • Never plan a renumber unless the ask demands it — it rewrites every inter-chapter link.
  • Every plan that adds or retitles a chapter includes the README TOC row and cross-link sweep as an explicit slice.

Output

✓ docs/plans/<YYYY>/<MM>/<DD>/<1NN>-<slug>/overview.md + 01-….md, … + status.yml
Next: run a writer on overview.md.

Read the full file on GitHub · 36 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. 4d ago First seen · 36 lines · 31 tokens per session scan A da0e0215911b

Subscribe to this mod's changes

planx is a command published in the GitHub repository sebyx07/claude-code-bible (5 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 673 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 2026-08-31.