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/open-curiosity/gini-agent/codexnpx skills add Open-Curiosity/gini-agent --skill codexgit clone --depth 1 https://github.com/Open-Curiosity/gini-agentWrote 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/open-curiosity/gini-agent/codex)<a href="https://agentmods.dev/skills/open-curiosity/gini-agent/codex"><img src="https://agentmods.dev/badge/skills/open-curiosity/gini-agent/codex.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 | $0.00023 | $0.00908 |
| Opus 5 | $0.00012 | $0.00454 |
| Sonnet 5 | $0.00005 | $0.00182 |
| Haiku 4.5 | $0.00002 | $0.00091 |
Grade A, and why
codex 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 3d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex CLI
Use the OpenAI Codex CLI when the user wants an autonomous coding pass in a git repository: feature work, bug fixes, refactors, review passes, or isolated experiments.
Prerequisites
- Install:
npm install -g @openai/codex - Authenticate with the Codex CLI login flow, or provide a valid OpenAI API key.
- Run inside a git repository. For scratch work, create a temporary repo first.
- Use
pty=truefor interactive Codex commands.
Codex CLI OAuth usually lives under ~/.codex/auth.json. Do not assume Codex
is unauthenticated only because OPENAI_API_KEY is missing.
When to Use
- User asks for a second coding agent to implement, review, or investigate.
- Work can be scoped to a repository, branch, or worktree.
- A task benefits from a separate autonomous pass while Gini keeps the main approval, audit, and trace path.
When NOT to Use
- User only needs a small direct edit that Gini can do faster.
- The working directory is not a git repo and the user did not ask for scratch prototyping.
- The request involves secrets, credential files, or destructive commands without explicit approval boundaries.
Quick Tasks
Run a focused one-shot from the target repo:
codex exec "Find why the dashboard test is flaky, patch the smallest fix, and run the targeted test."
Review local changes:
codex exec "Review git diff --stat and git diff for bugs, regressions, and missing tests. Return findings only."
Scratch prototype in a disposable repo:
tmp=$(mktemp -d)
cd "$tmp"
git init
codex exec "Create a tiny Bun CLI that parses a JSON file and prints a summary."
Long-Running Work
For long tasks, launch in the background with a PTY, then poll the process rather than starting duplicate Codex runs.
codex exec --full-auto "Refactor the settings loader. Keep the diff narrow and commit when tests pass."
Use --full-auto only when repository writes are expected and the user has
accepted the risk. Avoid --yolo unless the user explicitly asks for it.
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.
- 3d ago First seen · 125 lines · 23 tokens per session scan A 42837fc1027b
codex is a skill published in the GitHub repository Open-Curiosity/gini-agent (1,806 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 908 once invoked, about $0.0001 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
gget
Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST searches, AlphaFold structures, enrichment analysis. Best for interactive exploration, simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.
molecular-cloning
Molecular cloning simulation and design. PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation. For protein-level sequence analysis use biopython or esm; for database lookups use gene-database or ensembl-database.
curated-bio-datasets
Guide to accessing curated biological datasets for computational biology. COSMIC cancer data, GTEx expression, GWAS catalog, GeneBass exome variants, BioGRID interactions, MSigDB gene sets, DisGeNET disease-gene associations, and GO ontology. For specific database APIs use individual database skills (cosmic-database…
deeptools
NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.
flow-cytometry-analysis
Complete flow cytometry analysis pipeline. FCS file handling, compensation, manual/automated gating, immunophenotyping, CFSE proliferation analysis, cell cycle analysis (Dean-Jett-Fox), and apoptosis assays. Extends flowio with analytical workflows. For raw FCS parsing only use flowio.
flowio
Parse FCS (Flow Cytometry Standard) files v2.0-3.1. Extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame, for flow cytometry data preprocessing.