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.
git clone --depth 1 https://github.com/terrene-foundation/kailash-coc-claude-pyWrote 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.
[](https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/onboard)<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/onboard"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/onboard/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/onboard"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00033 | $0.01735 |
| Opus 5 | $0.00016 | $0.00868 |
| Sonnet 5 | $0.00007 | $0.00347 |
| Haiku 4.5 | $0.00003 | $0.00173 |
Grade A, and why
onboard 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard the operator into the current repo's multi-operator COC state. Read-only command — no commits, no state writes. Output is a structured briefing the operator (and the next session) can act on.
Run loom doctor FIRST. On a fresh / Windows / ADO clone, run node .claude/bin/loom-doctor.mjs (the /doctor command) before /onboard — it surfaces role/env/line-ending/VCS-host/resolver issues with remediations (and --fix repairs the safe subset). /onboard assumes a healthy clone; the doctor is what makes it one.
Usage: /onboard (no args; runs in current repo) — /onboard --json for machine-readable output
Process
/onboard is a deterministic read-path: every invocation surfaces the same artifacts in the same order, so two operators starting fresh sessions see consistent state. The procedure detail lives in the skill .claude/skills/41-onboard/SKILL.md; this command is the entry point.
1. Identify the operator
Resolve identity via .claude/hooks/lib/operator-id.js::resolveIdentity(). The result includes display_id, verified_id, and the operator's roster status. If the operator is not registered, surface the /whoami --register instruction and stop — onboarding past identity is not safe.
2. Read the team-memory surface
List every non-superseded <slug>.md under .claude/team-memory/ (skip the README.md governance file). For each file, surface:
- The topic slug (filename without
.md) - The body (≤80 lines per file by convention)
- The signed-attribution status (frontmatter
signed: true|false,promoted_by.display_id,proposal_ref)
Files failing integrity-guard.js validation (broken frontmatter, body-anchor mismatch, missing signed attribution where required) are reported in a separate "failed integrity" section. Do NOT show the body of a file with broken integrity — the file is treated as absent until repaired.
3. Read the active workspace + recent decisions
Run the same workspace-detection logic as multi-operator-sessionstart.js (the M5 hook):
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.
- 9d ago First seen · 93 lines · 33 tokens per session scan A 25e1e31bfa3f
onboard is a command published in the GitHub repository terrene-foundation/kailash-coc-claude-py (12 stars, last pushed 24d ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,735 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 2026-09-03.
Other commands, from other repositories
standup
Quick daily standup from today's Claude Code sessions — grouped by project, with cost and errors.
fire-todos
Capture, list, and manage todos during work sessions.
gsd:resume-work
Resume work from previous session with full context restoration.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
standup
A command that creates a daily stand-up report by summarizing recent work, planned tasks, calendar events, and blockers.
ops
Weekly operations loop — triage the inquiry inbox, advance the CRM pipeline, sweep open PRs across repos, and surface the content plan. Loads the ops skill.