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.
npx agentmods add commands/hdk10/orgkit/orgkit-initgit clone --depth 1 https://github.com/hdk10/orgkitWhat 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 | $0.00051 | $0.03334 |
| Opus 5 | $0.00026 | $0.01667 |
| Sonnet 5 | $0.00010 | $0.00667 |
| Haiku 4.5 | $0.00005 | $0.00333 |
Grade B, and why
orgkit-init scanned grade B 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.claude/settings.json` (creating it if missing). Watch the output: it may How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the intelligent onboarding agent for orgkit. Your job is NOT to run a Python heuristic and blindly accept its output. Your job is to read the repo yourself, understand what each folder actually IS, and propose a sensible org structure backed by real rationale.
The Python tool handles mechanics. You handle judgment.
Step 1 — Locate the repo and check onboarding state
The user's repo root is ${CLAUDE_PROJECT_DIR} (fall back to $PWD).
Check whether ${CLAUDE_PROJECT_DIR}/.org/roles.json already exists.
- If it exists: tell the user the repo is already an orgkit repo and suggest
/org-statusinstead. Use AskUserQuestion to ask whether they want to re-run onboarding (re-design roles from scratch) before continuing.
Step 2 — Extract deterministic folder signals
Run the scanner to get a compact, token-bounded signal payload.
Prefer the installed engine if it exists; fall back to the plugin copy:
# Use whichever exists:
# .org/scan.py — installed engine (preferred)
# ${CLAUDE_PLUGIN_ROOT}/orgkit/scan.py — plugin copy (pre-install fallback)
if [ -f "${CLAUDE_PROJECT_DIR:-$PWD}/.org/scan.py" ]; then
python3 "${CLAUDE_PROJECT_DIR:-$PWD}/.org/scan.py" --target "${CLAUDE_PROJECT_DIR:-$PWD}" --json
else
python3 "${CLAUDE_PLUGIN_ROOT}/orgkit/scan.py" --target "${CLAUDE_PROJECT_DIR:-$PWD}" --json
fi
Parse the JSON. You now have, for every top-level folder:
name— the folder name (may be cryptic:proj-final/,v2/,temp2/)file_count— total files insidetop_exts— top 5 file extensions with countskind— coarse classification: python / node / web / data / docs / infra / mixedtelltale— telltale files present (package.json, pyproject.toml, Dockerfile, etc.)excerpt— up to ~300 chars from the README or entry point
Step 3 — YOU reason over the signals (the intelligent step)
Do not fall back to keyword matching. Read the signals. For any folder where:
- the
kindismixedordocs, or - the name is cryptic / ambiguous (e.g.
v2/,experiments/,proj-final/,temp-client/), or - the excerpt is empty or unhelpful
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 · 246 lines · 0 tokens per session scan B 28166d45d601
orgkit-init is a command published in the GitHub repository hdk10/orgkit (2 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 3,334 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
update-changelog-and-tag
You are preparing a release. Follow these steps precisely.
plan-status
Render the current plan tree. Alias for /aura-frog:plan status (v3.7.2+).
help
Category: System Syntax: /help [command|topic].
_registry-protocol
This protocol is MANDATORY for ALL commands, agents, and phases.
mach12:issue-review
Read a GitHub issue and all comments, review the implementation plan, and present findings.
mach12:gh-pr-read
Read a GitHub pull request's title, body, and all top-level PR conversation comments; optionally locate an HTML-marker comment.