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/migrate)<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/migrate"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/migrate/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/migrate"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/migrate.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 | $0.00055 | $0.05706 |
| Opus 5 | $0.00028 | $0.02853 |
| Sonnet 5 | $0.00011 | $0.01141 |
| Haiku 4.5 | $0.00006 | $0.00571 |
Grade C, and why
migrate scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
**Implementation pattern (do NOT wholesale `cp -r sister/.claude/ ./.claude/`):** walk `$SISTER/.claude` per-file; write sister content for shared paths; preserve project-only files. The skill carries the canonical bash How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/migrate is the COC-adoption front door for an EXISTING repo. Two entry scenarios:
- (A) Adopt — a NON-COC-NATIVE repo (an existing codebase with no
.claude/COC tree):--adoptbootstraps COC in, selecting the right template family, then emits the per-CLI surfaces. - (B) Update — an OUTDATED-COC repo (COC present but stale): full migration upgrades a CC-only lineage to multi-CLI;
--refreshre-pulls multi-CLI overlays; a version-behind consumer routes to/sync-from-template.
Template families the co-owner named, all handled here:
- kailash —
kailash-coc-claude-{py,rs}(CC-only) +kailash-coc-{py,rs}(multi-CLI), for Kailash-SDK projects. - base —
coc-claude-base(CC-only) +coc-base(multi-CLI), the stack-agnostic non-Kailash templates (NOkailash-prefix; first-class COC consumers). - multi-CLI axis — the CC-only (
coc-claude-*) vs multi-CLI (coc-*/kailash-coc-{py,rs}) distinction WITHIN each family; that is the full-migration +--refreshsurface, not a separate family.
Project source, workspaces, journals, briefs, todos, .session-notes, .env, and SDK pins are preserved throughout. Detailed protocol (family detection, --adopt bootstrap steps, additive-merge semantics, 3-way reconciliation, verification table, marker schema, --emit-only non-COC lane): skills/30-claude-code-patterns/multi-cli-migration.md. Manifest source-of-truth: .claude/sync-manifest.yaml (repos: for target families/slugs, multi_cli_overlays: for the refresh set).
Modes
| Invocation | Behavior |
|---|---|
/migrate |
Detect repo state; RECOMMEND the right disposition (adopt / migrate / refresh / sync-from-template) per Step 0. Runs full migration on a CC-only lineage. |
/migrate --adopt |
Scenario A: bootstrap COC onto a repo with NO .claude/ tree. Auto-detects family (or --family kailash|base); defaults to multi-CLI (--cc-only for claude-only). |
/migrate --dry-run |
Detect + print every step's planned actions (adopt OR update); apply nothing. |
/migrate --refresh |
Multi-CLI consumer ONLY: re-pull top-level overlays per multi_cli_overlays.paths. |
/migrate --emit-only |
Non-COC lineage ONLY (e.g. claude-squad-local): emit .codex/, .gemini/, AGENTS.md, GEMINI.md from project's own .claude/. |
/migrate --rollback |
Inline porcelain guard, then git reset --keep main + restore from .pre-migrate.bak. |
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 · 147 lines · 55 tokens per session scan C f53a375cc729
migrate 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 55 tokens to every session and 5,706 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.