clean-instantiate

clean-instantiate is a command for Claude Code from terrene-foundation/kailash-coc-claude-py. It costs 36 tokens per session (1,612 once invoked), scanned A, original, Apache-2.0.

A guarded cleanup command for a freshly copied repository that removes the original project's operator and trust identity before setup. It runs as a dry run by default and requires human approval for destructive changes.

In plain words
What is it for?
Preparing a client clone for its own ecosystem by clearing inherited coordination records before initializing new ownership.
Why use it?
A copied repository can otherwise retain the original signing identity, operator list, journal, and other coordination data.

Command for Claude Code

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .claude/bin/clean-instantiate.mjs.

Good fit Preparing a client clone for its own ecosystem by clearing inherited coordination records before initializing new ownership.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/terrene-foundation/kailash-coc-claude-py
agentmods
npx agentmods add commands/terrene-foundation/kailash-coc-claude-py/clean-instantiate

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 clean-instantiate

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/clean-instantiate"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/clean-instantiate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,612 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 $0.00036 $0.01612
Opus 5 $0.00018 $0.00806
Sonnet 5 $0.00007 $0.00322
Haiku 4.5 $0.00004 $0.00161

Measured 7d ago against content hash 8e8151060e6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

clean-instantiate 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 7d 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/clean-instantiate.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/clean-instantiate — Strip Canon Identity From A Client Clone (once, before /ecosystem-init)

When a client clones, copies, or templates canon (loom + builds + use-templates) from GitHub to instantiate their own ecosystem, the clone inherits canon's committed coordination-substrate identity — the genesis trust-root, the operator roster (signing keys, owner identity), the journal, the team-memory facts, the ecosystem registry, the tenant denylist. /ecosystem-init does NOT clear these — it presumes the client owner is already enrolled. This command is the clear-then-bootstrap step that runs FIRST, on the client clone (canon is never touched).

It is the fourth onboarding surface, strictly BEFORE the other three: /clean-instantiate (once, on a fresh client clone) → /ecosystem-init (once per fork — re-anchors genesis to YOUR owner) → /enroll (once per operator) → /onboard (read-only, every session).

Usage: /clean-instantiate — runs in the current clone's checkout.

Procedure depth (the contamination-surface map, the assert-zero gate semantics, troubleshooting a fail-closed residual) lives in .claude/skills/46-clean-instantiate/SKILL.md per cc-artifacts.md Rule 3; this command is the entry point. The engine is .claude/bin/clean-instantiate.mjs; the "what counts as canon identity" judgement is the SHARED .claude/bin/lib/identity-scrub.mjs lib — the exact gate the public-fork publish fence uses, so the two fences cannot drift.

What it clears (plain language)

  • Operator roster → reset to a placeholder. Canon's owner identity, signing keys, and trust-root are removed; YOUR /ecosystem-init + /enroll re-establish them.
  • Decision journal (journal/) → deleted. Canon's recorded decisions are canon's, not yours.
  • Team-memory facts → cleared (the index README is kept).
  • Ecosystem registry (ecosystem.json) → reset to a placeholder, with upstream_canon pointed at the canon you cloned from (so your fork is recognised as a fork; the cross-ecosystem write-fence's operative activation stays gated on #576 — the entry-point hook is registered at F3 Level-1).
  • Tenant denylist → emptied.
  • Per-clone coordination state (logs, posture, lease, init markers) → cleared if a copy carried them.

Read the full file on GitHub · 108 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. 7d ago First seen · 108 lines · 36 tokens per session scan A 8e8151060e6f

Subscribe to this mod's changes

clean-instantiate is a command published in the GitHub repository terrene-foundation/kailash-coc-claude-py (12 stars, last pushed 23d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,612 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.