status

A command that reports the state of a personal knowledge collection, or “brain.” It counts knowledge areas and files, checks unprocessed files, lists recent output, and can calculate a health score for Markdown notes.

In plain words
What is it for?
Use it to review the collection’s size, recent additions, pending files, recent outputs, and the condition of its notes and cross-references.
Why use it?
It makes gaps in freshness, sources, indexing, links, and inbox processing visible in one summary. This helps identify where the knowledge collection needs maintenance.

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/lanzelot1/claw-brain/status
Clone the repo
git clone --depth 1 https://github.com/Lanzelot1/claw-brain

Made for: Claude Code.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 602 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 $0.00007 $0.00602
Opus 5 $0.00003 $0.00301
Sonnet 5 $0.00001 $0.00120
Haiku 4.5 $0.00001 $0.00060

Measured 2d ago against content hash 48d6027a00c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

status 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 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.

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/status.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Give the user a quick overview of the brain's current state.

Steps

  1. Read memory/_index.md and count:
    • Number of knowledge areas
    • Number of indexed files per area
    • Any entries under "Recently Added"
  2. Check drop/ for unprocessed files
  3. List the 5 most recent files in output/
  4. Present a clean, concise summary

Health Score

Calculate a health score (0-100) from these metrics. Skip this section entirely if there are no .md files in knowledge/.

Metric Weight How
Freshness 25% % of knowledge .md files with git commit <30 days
Source coverage 25% % with source: in YAML frontmatter
Index coverage 20% % referenced in memory/_index.md
Cross-references 15% % with ≥1 markdown link to another knowledge file
Inbox clear 15% 100 if drop/ is empty, 0 otherwise

Display as: Brain Health: X/100 with a breakdown table showing each metric's score.

Health Checks

After the score, run detailed health checks:

Check How
Freshness Run git log -1 --format="%ai" per knowledge .md file. Label: fresh (<30 days), aging (30-90 days), stale (>90 days)
Missing sources Check each .md file in knowledge/ for source: in YAML frontmatter. List any files missing it.
Orphaned files Find .md files in knowledge/ that are not referenced in memory/_index.md
Index coverage Compare file count in knowledge/ vs entries in _index.md
Cross-references Find knowledge files with no markdown links to other knowledge files

Present health results as a compact table or list. Only highlight problems — don't list every file if everything is healthy.

Wiki Health

Only display this section if any type: wiki files exist in knowledge/.

Check How
Wiki coverage Count wiki pages vs source files. Report ratio (not a score — there's no "right" number).
Stale wiki pages Wiki pages whose source files have been modified more recently than the wiki page's updated: date.
Unlinked sources Source files that aren't referenced in any wiki page's ## Sources section.
Contradictions Note any contradictions flagged in memory/log.md that haven't been resolved.

Read the full file on GitHub · 57 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. 2d ago First seen · 57 lines · 7 tokens per session scan A 48d6027a00c0

Subscribe to this mod's changes

status is a command published in the GitHub repository Lanzelot1/claw-brain (11 stars, last pushed 4mo ago), licensed MIT. It adds 7 tokens to every session and 602 once invoked, about $0.0000 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.