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/claim)<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/claim"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/claim/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/claim"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/claim.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 | $0.00047 | $0.01502 |
| Opus 5 | $0.00023 | $0.00751 |
| Sonnet 5 | $0.00009 | $0.00300 |
| Haiku 4.5 | $0.00005 | $0.00150 |
Grade A, and why
claim 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/claim — Multi-Operator Explicit Claim
Stake an explicit advisory claim on a path or glob. The same shape M2's adjacency-leasecheck.js writes on INDEPENDENT auto-claim — except /claim is the user-driven path: the operator says "I'm about to work on this; surface conflicts before I start."
Per multi-operator-coc architecture §4.1 + §4.2: claims are advisory (leases-advisory). Every adjacency-leasecheck severity is non-blocking — the §4.2 filesystem exception (git status --porcelain cross-worktree contention) surfaces as halt-and-report since loom#1323, and /claim itself emits halt-and-report on SAME and advisory on ADJACENT.
Usage
/claim <path-or-glob>
<path-or-glob>— repo-relative path (src/lib/foo.js) or glob (src/lib/**/*.js).
Flow
- Resolve identity via
.claude/hooks/lib/operator-id.js::resolveIdentity(cwd). If no signing key is configured, halt withnext: configure signing key, then run /whoami --register(architecture §6.1 block-into). - Read coordination log via filesystem Transport (
.claude/hooks/lib/transport-filesystem.js::createFilesystemTransport(repoDir)). - Fold via A2a's
foldLog(records, roster, {})(.claude/hooks/lib/coordination-log.js). Foldedaccepted[]is the authoritative active-claim view. - Project active sibling claims — filter
acceptedbytype === "claim", exclude ownverified_id, exclude released/reaped (rule 7 isClaimActive predicate). - Evaluate §4.1 relation via
.claude/hooks/lib/adjacency.js::sameReasonthenadjacentReasonagainst the candidate path. Pass{ phase, candidateCommits }opts where known (the optional axis-3 cohort promotion). - Dispatch by verdict:
- SAME → halt-and-report. Print the conflicting
claim_id, siblingdisplay_id, and the matched predicate (exact/glob/dir-contains/workspace/commit-cohort/phase/composed-axis-3— the full wiredadjacency.js::sameReasonpredicatereturn set). Do NOT append a claim record (this prevents the F2-1 race-to-write). Resolution routes through/release-claim, which self-releases ONLY the caller's own claims — the operator cannot release a sibling's claim directly. So: either the sibling self-releases (they run/release-claim <their-ref>), OR — if the sibling's claim is STALE — reap it via the cross-operator ceremony/release-claim --reap <conflicting-ref> --cosigner <person_id>(distinct-person cosigner + pinned-heartbeat-past-LIVENESS_TTL_MSper §4.4). There is nolease-overridecommand; do NOT direct the operator to one. - ADJACENT → write the claim record with
content.granted_relation = "ADJACENT"andcontent.advisory = true. Print the nearby sibling'sclaim_idand the matched predicate. - INDEPENDENT → write the claim record with
content.granted_relation = "INDEPENDENT". Silent success.
- SAME → halt-and-report. Print the conflicting
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.
- 7d ago First seen · 80 lines · 47 tokens per session scan A 3137dd1ee205
claim 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 47 tokens to every session and 1,502 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
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.