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.
git clone --depth 1 https://github.com/terrene-foundation/kailash-coc-claude-pynpx agentmods add commands/terrene-foundation/kailash-coc-claude-py/doctorWrote 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/doctor)<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/doctor"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/doctor/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/doctor"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/doctor.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 | $0.00904 |
| Opus 5 | $0.00016 | $0.00452 |
| Sonnet 5 | $0.00007 | $0.00181 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
doctor 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 8d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
loom doctor is the onboarding health-check. It surfaces EVERY onboarding issue
at once with an actionable remediation per finding — so a fresh operator on a
Windows / ADO / USE-consumer clone sees the full picture before /onboard,
not one cryptic failure at a time.
Modes. Read-only detection by default; --fix applies bounded SAFE repairs
(git config, the .coc-role marker with an explicit --role, the resolver
seed — never hook-mediated state); --json emits a versioned schema and
--strict exits non-zero on any CRIT for CI/ADO pipelines. The procedural
detail lives in the backing skill .claude/skills/47-loom-doctor/.
Steps
-
Run the check engine (read-only by default):
node .claude/bin/loom-doctor.mjs # human report node .claude/bin/loom-doctor.mjs --fix # apply safe repairs -
Present the report as-is (it is already grouped + all-at-once). Do NOT re-summarize away the per-finding remediation lines — the remediation IS the value (
user-flow-validation.md: the next step the user takes must be legible). -
For any
[CRIT]or[WARN]finding, restate the remediation in plain language percommunication.md(many onboarding operators are non-technical):- role: no role declared → "this clone hasn't been told whether it's a
platform / build / use-consumer checkout; create a
.coc-rolefile at the repo root with one of those words." - line-endings: core.autocrlf=true → "Windows line-ending auto-conversion
is on; it fights the repo's normalization. Turn it off with
git config core.autocrlf false." - vcs-host: no host authenticated → "you're not logged in to GitHub
(
gh) or Azure DevOps (az); log in to your host before onboarding." - resolver: link(s) fail to resolve → "one of your declared repo paths
points at a directory that isn't there; fix the path in
loom-links.local.json."
- role: no role declared → "this clone hasn't been told whether it's a
platform / build / use-consumer checkout; create a
-
If all checks are clean, say so plainly and point at
/onboardas the next step.
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.
- 8d ago First seen · 69 lines · 33 tokens per session scan A fd55c2227464
doctor 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 33 tokens to every session and 904 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
ci-debug
Diagnose a failing CI run against an 11-pattern playbook. Classifies the failure, cites the relevant memory entry, proposes the exact fix command — but NEVER applies without explicit user approval. Use when a specific PR check or GitHub Actions run failed and you want a diagnosis instead of speculation. Don't use for…
metrics
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
proxy-logs
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
traces
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
add-debug-wait
Add a wait step to a CI workflow for debugging test failures.
pr-quality-gate-reliability
You are reviewing a pull request for production survivability: how the change behaves when its dependencies misbehave, time out, or fail.