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 skills add htlin222/openevidence-mcp --skill openevidence-skillgit clone --depth 1 https://github.com/htlin222/openevidence-mcpWrote 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/skills/htlin222/openevidence-mcp/openevidence-skill)<a href="https://agentmods.dev/skills/htlin222/openevidence-mcp/openevidence-skill"><img src="https://agentmods.dev/badge/skills/htlin222/openevidence-mcp/openevidence-skill/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/skills/htlin222/openevidence-mcp/openevidence-skill"><img src="https://agentmods.dev/badge/skills/htlin222/openevidence-mcp/openevidence-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00111 | $0.01338 |
| Opus 5.5 | $0.00044 | $0.00535 |
| Sonnet 5.5 | $0.00022 | $0.00268 |
| Haiku 4.5 | $0.00011 | $0.00134 |
Grade A, and why
openevidence 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 1mo 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenEvidence (portable)
A stdlib-only Python port of openevidence-mcp. One CLI (scripts/oe.py) with four subcommands matching the MCP tools.
| MCP tool | Skill command | Purpose |
|---|---|---|
oe_auth_status |
python3 scripts/oe.py auth-status |
Confirm cookies.json still authenticates /api/auth/me |
oe_history_list |
python3 scripts/oe.py history |
Paginated question history with optional search |
oe_article_get |
python3 scripts/oe.py article <uuid> |
Fetch an article, extract answer + figures, save artifacts |
oe_ask |
python3 scripts/oe.py ask "<question>" |
Submit a new question, optionally wait, save artifacts |
Output of every command is a single JSON object on stdout - same shape the MCP returns to its client.
Setup (one time)
- Cookies. Export the OpenEvidence cookies from a logged-in browser tab (e.g. "Cookie-Editor" extension → "Export → JSON"). Save as
cookies.jsonnext to thisSKILL.md. The format is either a flat array of cookie objects or{ "cookies": [...] }(Playwright storage state). The file is gitignored. - Verify.
python3 scripts/oe.py auth-statusshould print"authenticated": true. Status401/403means the cookies expired - re-export.
Cookie lookup order: $OE_COOKIES, ./cookies.json, the skill folder, ~/.openevidence/cookies.json.
Common workflows
Ask a question, wait for completion, save artifacts (the default):
python3 scripts/oe.py ask "First-line therapy for adult community-acquired pneumonia in a hospitalized patient"
Note: behavior differs from the MCP tool. The MCP
oe_askis now fire-and-forget by default (returns a pendingarticle_id; passwait_for_completion:trueto block, or fetch later viaoe_article_get). THIS portable CLI waits by default — override with--no-wait.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 96 lines · 111 tokens per session scan A d40bb646641b
openevidence is a skill published in the GitHub repository htlin222/openevidence-mcp (81 stars, last pushed 20d ago), licensed Apache-2.0. It adds 111 tokens to every session and 1,338 once invoked, about $0.0004 per session on Opus 5.5. 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
nutrition
Review or plan fueling and hydration for training and racing.
why
Explain the evidence and uncertainty behind a training decision.
paper-retriever
Retrieve a scientific paper PDF given an arxiv URL, DOI, or paper title. Downloads to papers/ directory. Handles open-access retrieval (arxiv direct, Chrome print-to-pdf for publisher-direct HTML, Unpaywall, title-based open-repository search); for paywalled papers it hands off to whichever paper-retriever- access…
extract-claims
Extract propositional claims from a paper directory into the propstore source branch using pks source propose-claim.
paper-process
Retrieve a paper, read it, and run the full per-paper propstore ingestion flow through nested skills. Give it a URL, DOI, or title.
citation-verifier
Verify, normalize, and enrich a single citation or paper identifier. Use when the user pastes a DOI, URL, arXiv ID, PubMed ID, citation string, or paper title and wants it checked.