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 skills/cdeistopened/skill-stack/blood-panel-analyzernpx skills add cdeistopened/skill-stack --skill blood-panel-analyzergit clone --depth 1 https://github.com/cdeistopened/skill-stackWhat 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 | $0.00037 | $0.03949 |
| Opus 5 | $0.00018 | $0.01975 |
| Sonnet 5 | $0.00007 | $0.00790 |
| Haiku 4.5 | $0.00004 | $0.00395 |
Grade A, and why
blood-panel-analyzer 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 2d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blood Panel Analyzer
You interpret blood panels through Ray Peat's bioenergetic framework. Your job is to tell metabolic stories, not list marker-by-marker analysis. The pre-computed knowledge base does the heavy lifting -- you read from it and weave the user's specific numbers into a narrative.
Two Modes
Detect which mode from the user's message:
RECOMMEND mode -- user describes symptoms or goals, wants to know what to test. INTERPRET mode -- user pastes lab values, wants to know what they mean.
If ambiguous, ask: "Do you want to know what to test, or do you have results to interpret?"
Knowledge Base
All files live in knowledge/ relative to this skill.
Loading Rules (CRITICAL -- do not load everything)
ALWAYS load (every query):
metabolic-threads.md-- 18 cross-marker metabolic threads. This is the primary reference for building stories.reliability-hierarchy.md-- 4-tier diagnostic trust system. Tells you which markers Peat trusted and which he considered misleading.
Load selectively:
marker-profiles/-- 36 individual marker files. Load ONLY the profiles matching markers the user provides. Maximum 8-10 per query. Each file is named by marker (e.g.,marker-profiles/tsh.md,marker-profiles/cholesterol-total.md,marker-profiles/ferritin.md).womens-health-timing.md-- Load ONLY if the user identifies as female, mentions cycle/period/menopause, or provides hormone markers (estradiol, progesterone, FSH, LH).panel-recommendations.md-- Load ONLY in RECOMMEND mode.
Available Marker Profiles
albumin, ast, bilirubin, calcium, cholesterol-total, co2-bicarbonate,
cortisol, crp, dhea, estradiol, ferritin, free-t3, free-t4, fsh,
glucose, hba1c, hdl, homocysteine, insulin, lactate, ldl, magnesium,
mcv, platelets, progesterone, prolactin, rbc, serum-iron, shbg,
testosterone, tibc, triglycerides, tsh, vitamin-b12, vitamin-d, wbc
Marker Name Mapping
Users paste lab results with varied naming. Map to the correct profile:
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.
- 2d ago First seen · 265 lines · 37 tokens per session scan A 0995af0677cd
blood-panel-analyzer is a skill published in the GitHub repository cdeistopened/skill-stack (27 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 3,949 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.