enroll

enroll is a command for Claude Code from terrene-foundation/kailash-coc-claude-py. It costs 38 tokens per session (1,756 once invoked), scanned A, original, Apache-2.0.

An onboarding command for registering one operator in an already configured project ecosystem. It records the operator in a shared roster and creates local links for that operator's machine.

In plain words
What is it for?
Use it when joining an existing ecosystem for the first time, before continuing with the project's onboarding steps.
Why use it?
It gives new contributors the required shared registration and local setup in one process.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

Good fit Use it when joining an existing ecosystem for the first time, before continuing with the project's onboarding steps.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/terrene-foundation/kailash-coc-claude-py/enroll
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.

Clone the repo
git clone --depth 1 https://github.com/terrene-foundation/kailash-coc-claude-py

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 enroll

README.md
[![agentmods](https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/enroll/github.svg)](https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/enroll)
Your own site
<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/enroll"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/enroll/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.

agentmods 80×15 button for enroll

Your own site · 80×15
<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/enroll"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/enroll.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,756 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00038 $0.01756
Opus 5 $0.00019 $0.00878
Sonnet 5 $0.00008 $0.00351
Haiku 4.5 $0.00004 $0.00176

Measured 8d ago against content hash a2805e852a2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

enroll 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 8d 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/enroll.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/enroll — Onboard an Operator (once per operator/ecosystem)

The once-per-operator ceremony a human runs when joining an EXISTING ecosystem (one already configured by /ecosystem-init). One of the three onboarding surfaces — distinct from /ecosystem-init (once per fork) and /onboard (read-only, every session); see (loom-internal reference).

Usage: /enroll (no args; runs in the operator's checkout of an already-configured ecosystem)

/enroll does TWO writes — the roster registration (shared, PR-gated) and the per-operator local-links (gitignored, machine-local) — then hands off to /onboard. It does NOT re-implement either write: B1 delegates to the existing /whoami --register path (the ONLY roster-write path), B2 writes the existing per-operator gitignored layer. Procedure detail lives in .claude/skills/44-enroll/SKILL.md per cc-artifacts.md Rule 3; this command is the entry point.

The three invariants (load-bearing — the redteam surface)

  1. B1 roster registration wraps the EXISTING /whoami --register path. Roster registration is the 2-of-N-quorum PR-gated write described in multi-operator-coordination.md §1 — the ONLY roster-write path. /enroll does NOT re-implement it; it invokes /whoami --register (derive person_id, cut the codify/<id>-<date> branch off main, schema-validate, commit, push, open PR). NEVER writes operators.roster.json directly to main (branch protection rejects it).
  2. B2 local-links is per-operator gitignored — NO disclosure gate. The NAME→on-disk-path layer (loom-links.local.json, loom-links.mjs precedence $LOOM_LINKS_CONFIG > local > fail-loud) is per-operator/per-machine and gitignored — it NEVER syncs and NEVER reaches a committed/public surface, so the #255 disclosure gate that /ecosystem-init C1 runs does NOT apply here. (Contrast: the ecosystem-SHARED remote_links IS disclosure-fenced; the per-operator LOCAL layer is not, because it never leaves the machine.)
  3. B3 hands off to /onboard/enroll does not do the session-entry reads itself. Roster + posture
    • team-memory + claims reads are /onboard's read-only job (knowledge-convergence.md MUST-5); /enroll writes identity once, then points the operator at /onboard for every subsequent session.

Read the full file on GitHub · 101 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. 8d ago First seen · 101 lines · 38 tokens per session scan A a2805e852a2b

Subscribe to this mod's changes

enroll 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 38 tokens to every session and 1,756 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.