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/andyzhuang/opentest/detect_common_wetlab_errorsnpx skills add AndyZhuang/Opentest --skill detect_common_wetlab_errorsgit clone --depth 1 https://github.com/AndyZhuang/OpentestWrote 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/andyzhuang/opentest/detect_common_wetlab_errors)<a href="https://agentmods.dev/skills/andyzhuang/opentest/detect_common_wetlab_errors"><img src="https://agentmods.dev/badge/skills/andyzhuang/opentest/detect_common_wetlab_errors.svg" alt="Measured on agentmods" 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 | $0.00077 | $0.03845 |
| Opus 5 | $0.00039 | $0.01922 |
| Sonnet 5 | $0.00015 | $0.00769 |
| Haiku 4.5 | $0.00008 | $0.00384 |
Grade A, and why
detect_common_wetlab_errors 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 6d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detect Common Wet-Lab Errors
Overview
detect_common_wetlab_errors is a video-based error detection layer for the LabOS lab safety and compliance stack. It analyzes XR headset or fixed-camera footage to identify observable wet-lab mistakes — pipette volume mismatches, skipped reagent additions, uncapped tubes before centrifugation, cross-contamination risks, sample labeling errors, and protocol-agnostic hazards — that may not be caught by protocol-step matching alone. Each detected error is emitted as a structured JSON record with type, timestamp, severity, affected object, and a suggested corrective action, enabling real-time XR alerts, post-experiment audit reports, or integration with protocol_video_matching for a unified compliance dashboard.
When to Use This Skill
Use this skill when any of the following conditions are present:
- Real-time safety monitoring: A live XR or bench camera feed must be monitored for common procedural errors so the operator can be alerted immediately (e.g., "Tube uncapped before centrifuge — cap before spinning").
- Post-hoc experiment audit: A recorded experiment video must be scanned for errors that could explain failed or inconsistent results — forgotten reagent, wrong tube, contamination event.
- Training and quality assurance: A trainee's recorded run must be reviewed for error patterns; the skill flags occurrences for feedback and coaching.
- Protocol-agnostic error detection: Errors that are universally hazardous (uncapped tube in centrifuge, pipette tip reuse across samples) must be detected even when no protocol context is available.
- Complement to protocol matching:
protocol_video_matchingdetects step deviations; this skill detects physical/safety errors that may or may not align with protocol steps — use both for comprehensive compliance. - Root cause analysis: An experiment failed; the video is re-analyzed to identify whether a detectable error (e.g., reagent not added, tube mix-up) could explain the failure.
- GMP/GLP documentation: A regulated workflow requires documented evidence of error detection and correction; the skill's JSON output serves as an audit trail.
- Lab automation handoff: Before a human hands samples to a robot (Opentrons, Hamilton), the skill verifies that tubes are capped, labels are visible, and no obvious contamination is present.
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.
- 6d ago First seen · 266 lines · 77 tokens per session scan A aa92dd3a7e1a
detect_common_wetlab_errors is a skill published in the GitHub repository AndyZhuang/Opentest (22 stars, last pushed 5mo ago), licensed MIT. It adds 77 tokens to every session and 3,845 once invoked, about $0.0004 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…