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/sync-from-downstream)<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/sync-from-downstream"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/sync-from-downstream/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/sync-from-downstream"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/sync-from-downstream.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 | $0.01188 |
| Opus 5 | $0.00016 | $0.00594 |
| Sonnet 5 | $0.00007 | $0.00238 |
| Haiku 4.5 | $0.00003 | $0.00119 |
Grade A, and why
sync-from-downstream 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ingest the downstream upflow inbox INBOUND at a USE template. /sync-from-downstream brings consumer-originated COC-artifact proposals (offered by a downstream coc-project via its /codify Step-7c, as a human-gated PR to .claude/.proposals/inbox/<date>-<slug>.yaml) into this template, then relays accepted entries up to loom on the template's own proposal stream.
Detailed protocol: skills/30-claude-code-patterns/sync-flow.md § Template Inbox Ingest.
Usage: /sync-from-downstream — no target.
Step 0: Verify Repo Class (this verb is for USE templates)
Read .claude/VERSION → type. /sync-from-downstream is valid ONLY at a USE template (type: coc-use-template). MUST verify the declaration is credible before routing — but verify it against this repo's own declaration, never a hardcoded name list: compare .claude/VERSION::repo (the <owner>/<name> slug the VERSION was authored FOR) against this repo's git remote get-url origin. Names agree → confirmed template. Names disagree on two real git identities → the "Use this template" byte-copy case. .claude/hooks/lib/version-utils.js::classifyTemplateDeclaration is the single predicate; do not re-derive it here.
A hardcoded canonical set (kailash-coc-claude-{py,rs,rb}, kailash-coc-{py,rs}, coc-base / coc-claude-base) survives ONLY as a legacy silencer for canon templates that have not yet been stamped with their own repo — it can never recognize a client-fork template, whose name canon has never heard of, and a fork template must NOT self-mis-classify as a downstream coc-project merely for being absent from a list written at canon. /sync-to-use Step 2 stamps repo when the coc-sync agent runs the stamper as documented — nothing in the engine enforces it, so the list drains only as templates are re-synced by an agent that followed that step. Treat an unstamped template as expected during the migration window, not as evidence it is a copy.
coc-use-template(verified) → proceed below.coc-source(loom) → STOP: "this is loom — ingest the upstream streams with/sync-from-build+/sync-from-use."coc-project→ STOP: "this is a downstream consumer — pull from your template with/sync-from-template."coc-build→ STOP: "BUILD repos receive artifacts via/sync-to-buildrun at loom."- Declaration NOT credible (
VERSION::reponames a different repo than this one's git remote) → STOP and report; do NOT silently re-route on a class you just decided to disbelieve. Correcting it is an EXPLICIT, reviewable edit the operator approves: settype: coc-projectand populateupstream({template, template_repo, template_version, synced_at, sdk_packages}—.claude/hooks/lib/version-utils.js::computeTemplateDerivedCorrectionreturns the suggested object; it is PURE and writes nothing), then run/sync-from-template. NEVER rewrite.claude/VERSIONsilently or as a side effect — it is the repo-CLASS root of trust (bin/lib/manifest-source.mjs::readRepoClasstruststypeverbatim), which is whyvalidate-bash-command.jsBLOCKS agent writes to it at the Bash boundary. - Declaration undetermined (no
VERSION::repo, no legacy-list match) → report the ambiguity and ask; do not guess a class. - Missing → ask the user what class this repo is.
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 · 44 lines · 33 tokens per session scan A f3b532e2535f
sync-from-downstream 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 1,188 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
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
sync
Synchronizes your local swarm state with the latest GitHub repository state, updating task statuses and detecting changes.
claim
Claims a GitHub issue for your swarm to work on, preventing conflicts with other swarms.
repo-architect
Repository structure optimization and multi-repo management with ruv-swarm coordination for scalable project architecture and development workflows.
weekly-summary
Generate weekly work summary from git activity.
next
Suggest the most likely next workflow action based on current context.