org-status

A command that summarizes the current state of an organization stored in project files. It reports roles, registered folders, outdated role information, pending work, and folders that do not match the records.

In plain words
What is it for?
Use it to review role ownership, folder coverage, promotion age, pending activity, and missing or unmapped folders.
Why use it?
It gives a quick view of organizational drift and work that may need attention instead of requiring several files to be checked manually.

Command

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/hdk10/orgkit/org-status
Clone the repo
git clone --depth 1 https://github.com/hdk10/orgkit
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 928 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 $0.00040 $0.00928
Opus 5 $0.00020 $0.00464
Sonnet 5 $0.00008 $0.00186
Haiku 4.5 $0.00004 $0.00093

Measured yesterday against content hash 3bb874b95f06, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

org-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 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.

commands/org-status.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Show me the current state of the org.

Steps

  1. Regenerate ORG.md and ORG_PLAN.md to ensure they reflect the current filesystem:

    python3 .org/sync_org.py
    

    If the script errors, report the error and continue with whatever ORG.md / ORG_PLAN.md exist on disk.

  2. Read .org/roles.json, ORG.md, and ORG_PLAN.md (if present).

  3. For each role, collect:

    • Role name and desc from roles.json.
    • Number of registered folders in roles.<role>.folders.
    • Presence of .last_promote marker at <role>/memory/.last_promote — read it (JSON with ts and iso keys) and compute days since promotion.
    • Presence and non-emptiness of <role>/memory/_pending.md — check if it contains any non-drained, non-comment lines (i.e., real pending content beyond a "Drained" marker line).
  4. Check for drift by reading ORG.md for any "Unmapped" or "Missing" sections generated by sync_org.py. Collect them.

  5. Render a status table using this format:

    Org Status — <today's date>
    ═══════════════════════════════════════════════════════
    
    ROLES
    ──────────────────────────────────────────────────────
    Role          Folders   Brain age     Pending   Action
    ──────────────────────────────────────────────────────
    <role>        <N>       <X>d ago      YES/NO    <tag>
    ...
    
    Action tags:
      STALE+PENDING → run /role-promote <role>   (brain >7d old AND has pending content)
      STALE         → consider /role-promote <role>  (brain >7d old, no pending)
      PENDING       → run /capture <role> then /role-promote <role>  (pending, brain fresh)
      OK            → nothing needed
    
    ──────────────────────────────────────────────────────
    DRIFT
    ──────────────────────────────────────────────────────
    Unmapped folders (on disk, not in any role):  <list or "none">
    Missing folders  (in roles.json, not on disk): <list or "none">
    
    ──────────────────────────────────────────────────────
    SUMMARY
    <N> roles | <M> STALE+PENDING | <K> STALE | <J> PENDING | <X> unmapped | <Y> missing
    
  6. If any roles are STALE+PENDING, list them explicitly at the bottom as a recommended action list:

    Recommended actions:
      /role-promote <role>   — <N> days stale, has pending content
      ...
    
  7. If ORG_PLAN.md exists, read it and display:

    • The progress bar line (e.g. Progress: ███████░░░ 7/12 done)
    • Up to 3 next unchecked items with their hints, formatted as:
      Adoption plan (ORG_PLAN.md):
        Progress: ███████░░░ 7/12 done
        Next up:
          [ ] <item text>
              → <hint>
      

    If ORG_PLAN.md does not exist, suggest running python3 .org/plan.py to generate it.

Read the full file on GitHub · 81 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. yesterday First seen · 81 lines · 40 tokens per session scan A 3bb874b95f06

Subscribe to this mod's changes

org-status is a command published in the GitHub repository hdk10/orgkit (2 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 928 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.