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 srikarjy/Biolab-mcp-server --skill evidence-workspacegit clone --depth 1 https://github.com/srikarjy/Biolab-mcp-serverWrote 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/srikarjy/biolab-mcp-server/evidence-workspace)<a href="https://agentmods.dev/skills/srikarjy/biolab-mcp-server/evidence-workspace"><img src="https://agentmods.dev/badge/skills/srikarjy/biolab-mcp-server/evidence-workspace/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/srikarjy/biolab-mcp-server/evidence-workspace"><img src="https://agentmods.dev/badge/skills/srikarjy/biolab-mcp-server/evidence-workspace.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 | $0.00039 | $0.00394 |
| Opus 5.5 | $0.00016 | $0.00158 |
| Sonnet 5.5 | $0.00008 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
evidence-workspace 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 11d 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.
What it actually says
Biolab Evidence Workspace
Use Biolab as the source-of-record layer. Distinguish retrieved source material, agent interpretation, and human review at all times.
Search
For a broad scientific question, call search_evidence with only relevant
sources. Begin with a small result limit, inspect explicit source errors, and
preserve each returned retrieval_id in downstream notes.
For a source-specific question, prefer its dedicated tool. Never claim that a search result validates a mechanism, causal relationship, clinical intervention, or experimental conclusion.
Verify
Call get_retrieval before quoting or relying on a previously retrieved item.
Compare the interpretation with the normalized snapshot and raw response. A
retrieval ID is evidence provenance, not a quality score.
Organize
Before creating or changing a project, collection, or watch, summarize the intended mutation and obtain user approval when the host requests it.
- Create or select a project.
- Create a focused evidence collection.
- Add retrievals with an explicit relevance state and concise human-review note.
- Keep conflicting and excluded evidence rather than silently deleting it.
Monitor
Create a watch only for a query and source the user wants monitored. Running a watch contacts the external source, writes new retrieval records, and may create added, removed, or content-changed events. Report changes and source errors.
Boundaries
- Do not provide clinical advice.
- Do not send patient or sensitive data to a public deployment.
- Do not equate Open Targets scores with proof of causal biology.
- Do not equate UniProt review status with validation of a therapeutic claim.
- Require scientist review before experimental or clinical decisions.
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.
- 11d ago First seen · 50 lines · 39 tokens per session scan A 5eb04185ca75
evidence-workspace is a skill published in the GitHub repository srikarjy/Biolab-mcp-server (0 stars, last pushed 5d ago), licensed MIT. It adds 39 tokens to every session and 394 once invoked, about $0.0002 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 2026-10-04.
Other skills, from other repositories
biotech-expert
Expert in biotechnology systems, genomics, LIMS, bioinformatics pipelines, lab automation, and bioprocess management. Use when the user mentions genomics, bioinformatics, LIMS, lab automation, bioprocessing, or gene sequencing, or when the task involves Genomics and Sequencing Technologies, Laboratory Information…
neuropixels-analysis
Analyzes Neuropixels extracellular recordings end-to-end with SpikeInterface. Covers loading SpikeGLX/Open Ephys/NWB data, preprocessing, drift/motion correction, Kilosort4 (and CPU) spike sorting, quality metrics, and unit curation (threshold-based, model-based UnitRefine, and AI-assisted visual review). Use when…
onekgpd
Queries the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which…
biopython
Provides Biopython workflows for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Supports batch processing, custom molecular-biology pipelines, BLAST automation, structure analysis, and motif analysis.
experimental-design
Designs experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so results are interpretable. Use whenever someone is planning a study, asks how to assign subjects/samples to groups, mentions randomization, blocking, stratification, controls…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.