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.
npx agentmods add commands/polygraphso/litmus/checkgit clone --depth 1 https://github.com/polygraphso/litmusWhat 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 | $0.00014 | $0.00261 |
| Opus 5 | $0.00007 | $0.00130 |
| Sonnet 5 | $0.00003 | $0.00052 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
check 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 yesterday.
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.
What it actually says
Use the verify_attestation tool from the polygraph-litmus MCP server (bundled
with this plugin) to read the published polygraph grade for $ARGUMENTS. If it
returns not_available, say the server is unevaluated (neither safe nor unsafe)
and offer to grade it live with /polygraph:grade. If it returns lookup_failed,
say the lookup itself failed so the grade is unknown — do not call it
unevaluated. (To read a published skill grade, use verify_skill_attestation
instead.)
If verify_attestation isn't in your available tools, it may just need loading
(some clients surface MCP tools lazily) — try to load it before concluding it's
missing. Only if the polygraph-litmus server genuinely isn't connected, tell me
to enable the plugin (/plugin install polygraph@polygraphso, adding the
marketplace first with /plugin marketplace add polygraphso/litmus if needed)
and restart the session so the tools load. Do not suggest claude mcp add — the
plugin already provides the server.
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.
- yesterday First seen · 20 lines · 14 tokens per session scan A 7c3067928b7c
check is a command published in the GitHub repository polygraphso/litmus (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 261 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
design-review
Workflow recipe — review a design end-to-end, ending in measured numbers rather than adjectives, by chaining 4 skills.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
security-review
CWE 기반 보안 검토 + STRIDE 위협 모델링 (v6 - effort:max 강제).
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
release-harn
Run the tag-first Harn release workflow.