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/worktree)<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/worktree"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/worktree/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/worktree"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/worktree.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 | $0.00037 | $0.02032 |
| Opus 5 | $0.00018 | $0.01016 |
| Sonnet 5 | $0.00007 | $0.00406 |
| Haiku 4.5 | $0.00004 | $0.00203 |
Grade A, and why
worktree 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/worktree — dedicated sibling worktree for parallel development
Creates a durable, session-rootable git worktree OUTSIDE the repo (a sibling), so a
session can work in parallel with another operator on the same clone WITHOUT (a) colliding on
the shared working tree, (b) duplicating the path-scoped rule corpus, or (c) placing a full nested
checkout INSIDE the repo's own .claude/** glob range, where parent-repo recursive tooling (a
grep -r / a validator run with --root .) descends into it and pulls a duplicate corpus in as
tool output — plus the human-org clutter of a ~24MB checkout in the working tree.
On (b): a session rooted at a NESTED worktree was measured (2026-07-26, CC 2.1.220, untracked-sentinel
probe) to load path-scoped rules from BOTH its own .claude/rules/ AND the ancestor repo's — the
same rule twice, under two paths — while a SIBLING-rooted session loads each exactly once. CLAUDE.md
and baseline (priority: 0) rules do NOT ancestor-load. Sibling placement is therefore a quota
requirement, not a tidiness preference — for a worktree a SESSION ROOTS INTO; a dispatched subagent
inherits its parent session's corpus instead (measured) and is not itself a double-load.
Full rationale + measured matrix + repro protocol:
rules/worktree-isolation.md Rule 7 and skills/30-claude-code-patterns/worktree-orchestration.md
§ Ancestor-Load Measurement.
Durable session worktrees and transient agent-wave worktrees BOTH live outside the repo now:
rules/worktree-isolation.md Rule 1 retired isolation: "worktree" / EnterWorktree({name}),
the flags that placed agent waves under .claude/worktrees/. They differ in LIFECYCLE, not
placement. Use /worktree for a human/session worktree you root into and keep across tasks;
for a wave, the orchestrator makes a transient per-shard sibling with git worktree add directly,
dispatches with the absolute path pinned AND a mandated STEP-0 cwd assertion (skills/30-claude-code-patterns/worktree-orchestration.md
§ Retiring isolation: "worktree"), and MUST reap it at the wave's terminal-lane transition
(rules/worktree-isolation.md Rule 8; procedure + tiering in that skill's § Teardown). A session that roots into its worktree (this command, step 3) gets the
cwd guarantee from the launch/re-root itself, so it needs no such assertion — a DISPATCHED agent
does, because nothing sets its cwd once the flag is gone.
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 · 90 lines · 37 tokens per session scan A 0904c9688d1c
worktree 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 37 tokens to every session and 2,032 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
handoff
Export a Waybill Bundle by default, or import one when requested.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.