audit-langfuse-llm SKILL.md skillA
This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.
audit-langfuse-llm from kensaurus/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kensaurus/skills/audit-langfuse-llm@git:20260926.c7354acPins git:20260926.c7354ac in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kensaurus/skills
- Path
skills/audit-langfuse-llm/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260926.c7354ac, committed Sep 26, 2026
- First version recorded
- Sep 12, 2026
- Size
- 15,401 bytes
- Repository stars
- 9
- License
- MIT
PDCA quality audit of LLM features: traces, prompts, costs, evals, grounding, hallucination. Use for "audit LLM quality", "check Langfuse", or "audit AI costs". Jailbreaks → audit-llm-security. Cost caps → plan-llm-cost-guardrails.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Langfuse LLM Quality Audit **Degree of freedom: MIXED** — Phases 0–1, 4 `[HIGH freedom]`; Phases 2–3 CLI traces and playwright `[LOW freedom — run exactly]`. Read `protocol-browser-anti-stall` before any browser step. Phase 0 first: Phases 2–3 verify the feature map it produces. ## How to reason 1. **Observe** — quote the trace, prompt version, token/cost, or live output 2. **Interpret** — is quality, cost, or the pipeline actually broken? 3. **Classify** — missing-trace / prompt / cost / eval / grounding / correct 4. **Severity** — pipeline break or untraced prod feature = P0; cost/eval gap = P1 ## Worked example > **Observe:** after Playwright chat, `langfuse-cli api traces list` shows no new > row; `app/api/chat/route.ts` calls `openai.chat` with no Langfuse wrap. > **Interpret:** the live path is uninstrumented — the static map was wrong. > **Classify:** missing instrumentation (pipeline break). > **Severity:** P0 — prod chat is invisible. > **Finding:** chat | P0 | no trace after live send | wrap the SDK call. ## Self-critique before reporting [LOW freedom — do not skip] 1. **Concrete numbers** — model + $/call or tokens, not "costs seem high" …
Read the whole file at its exact version.
How to install
mdr add kensaurus/skills/audit-langfuse-llm@sha256:a29fefa66db66a22The line at the top of this page pins the label git:20260926.c7354ac, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_4pnoxxmnvafnkid5)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 12, 2026 and Sep 26, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260926.c7354ac latest | 2026-09-26 | c7354ac | 15,401 B | A | view · diff |
| git:20260923.938ff43 | 2026-09-23 | 938ff43 | 15,454 B | A | view · diff |
| git:20260923.68c095e | 2026-09-23 | 68c095e | 15,527 B | A | view · diff |
| git:20260923.cf348bd | 2026-09-23 | cf348bd | 15,545 B | A | view · diff |
| git:20260912.33d48b1 | 2026-09-12 | 33d48b1 | 15,488 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (15401 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
kensaurus/skills · 9 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_4pnoxxmnvafnkid5 GET https://markdownregistry.com/api/v1/resolve?ref=kensaurus/skills/audit-langfuse-llm GET https://markdownregistry.com/api/v1/blob/a29fefa66db66a22c50faf5129e6d73086590e29ab847827b583843d6a146cac
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from kensaurus/skills
Every file in kensaurus/skills