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/evo-design/proto-tools/implement-toolnpx skills add evo-design/proto-tools --skill implement-toolgit clone --depth 1 https://github.com/evo-design/proto-toolsWhat 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 | $0.00093 | $0.14576 |
| Opus 5 | $0.00046 | $0.07288 |
| Sonnet 5 | $0.00019 | $0.02915 |
| Haiku 4.5 | $0.00009 | $0.01458 |
Grade A, and why
implement-tool scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
wget -q -O "$WEIGHTS_DIR/model.pt" "https://example.com/model.pt" How it starts
The opening of the file, as written. The whole thing — 996 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement a New Tool — Orchestrator Pipeline
You are implementing a new bioinformatics tool in the proto-tools codebase. This skill orchestrates the full lifecycle using parallel subagents for speed.
Pipeline overview:
Phase 1: Research → Phase 2: Contract → Phase 3: Fan-out (5 parallel agents) → Phase 4: Verify → Phase 4.5: Config Field Audit → Phase 4.6: Temp Integration & Stress → Phase 4.7: Docs Verification → Phase 4.8: Self-Audit & Full PR Review → Phase 5: Ship
The Phase 4.x gates are decisive and non-negotiable — they catch the failure modes that the fast fan-out reliably misses (invented config parameters, untested real workloads, hallucinated citations/licenses, missing license.yaml/links.yaml). Do not skip them to ship faster. Ground every decision in upstream source or a credible reference — never assume.
Key principle: The core tool file (Input/Config/Output + @tool() + run_*()) is the contract everything else depends on. Write it first (sequential), then fan out to subagents (parallel).
CRITICAL: Standalone scripts run in isolated environments and MUST NOT import from proto_tools:
from proto_tools.utils import ...— will fail at runtimefrom proto_tools.entities import ...— will fail at runtimefrom standalone_helpers import get_subprocess_device_env— published on PYTHONPATH (OK)- Standard library imports:
import json,import subprocess, etc. (OK) - Dependencies from
requirements.txt:import torch,import numpy, etc. (OK) - NEVER install
proto_toolsin standalone environments (creates circular dependency, breaks isolation)
Phase 0: Parse Input
The user provides EITHER:
- A GitHub issue URL/number (e.g.,
#<issue-number>orhttps://github.com/evo-design/proto-tools/issues/<issue-number>) - A tool name + source repo (e.g., "ESM-IF from https://github.com/facebookresearch/esm")
If a GitHub issue is provided:
- Fetch the issue with
gh issue view <number> --json title,body,labels - Extract from the issue body: tool name, source repo URLs, paper links, category, operations
- Present the extracted info to the user for confirmation
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.
- 2d ago First seen · 996 lines · 93 tokens per session scan A ed8e78fa1acf
implement-tool is a skill published in the GitHub repository evo-design/proto-tools (125 stars, last pushed 5d ago), licensed MIT. It adds 93 tokens to every session and 14,576 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cellxgene-census-query
Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets…
functional-analysis
Understand the biological meaning of gene sets through pathway and functional enrichment analysis. Use when user has gene lists (DEGs, markers, SVGs) and wants to know what pathways or functions they represent. Triggers: "pathway analysis", "enrichment", "GSEA", "GO terms", "what pathways", "biological function"…
troubleshoot
Diagnose and resolve common issues in spatial transcriptomics analysis. Use when analysis fails, produces unexpected results, or user encounters errors. Triggers: "error", "failed", "not working", "issue", "problem", "help", "unexpected result", "debug", "fix", "wrong output".
cell-composition
Determine cell type composition at each spatial location through deconvolution or annotation. Use when user wants to know what cell types exist, their proportions, or where specific cells are located. Triggers: "cell type composition", "deconvolution", "what cells are here", "cell type proportions", "estimate cell…
cell-dynamics
Understand cellular differentiation, state transitions, and dynamic processes through trajectory and velocity analysis. Use when user wants to study development, differentiation, cell fate decisions, or temporal dynamics. Triggers: "trajectory", "pseudotime", "RNA velocity", "differentiation", "cell fate", "how do…
differential-analysis
Find differentially expressed genes between conditions, regions, or cell types. Use when user wants to compare gene expression, find markers, or identify condition-specific changes. Triggers: "differential expression", "DEG", "marker genes", "compare conditions", "what genes differ", "find markers", "condition…