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/agentconfig/agentconfig.org/add-primitivenpx skills add agentconfig/agentconfig.org --skill add-primitivegit clone --depth 1 https://github.com/agentconfig/agentconfig.orgWrote 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/agentconfig/agentconfig.org/add-primitive)<a href="https://agentmods.dev/skills/agentconfig/agentconfig.org/add-primitive"><img src="https://agentmods.dev/badge/skills/agentconfig/agentconfig.org/add-primitive.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 | $0.00035 | $0.01897 |
| Opus 5 | $0.00017 | $0.00949 |
| Sonnet 5 | $0.00007 | $0.00379 |
| Haiku 4.5 | $0.00003 | $0.00190 |
Grade A, and why
add-primitive 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Primitive
Add or modify AI primitive definitions for agentconfig.org.
Overview
Primitives appear in these places:
- Primitive Cards -
site/src/data/primitives.ts(the single canonical source) - File Tree -
site/src/data/fileTree.ts - Provider Comparison -
site/src/data/comparison.ts(derived automatically fromprimitives.ts; never hand-edited) - Provider Profiles -
site/src/data/providerProfiles.ts(also derived automatically fromprimitives.ts; never hand-edited)
Step-by-Step Process
1. Define the Primitive
Edit site/src/data/primitives.ts:
{
id: 'your-primitive-id', // lowercase, hyphens
name: 'Display Name',
description: 'One-sentence summary.',
whatItIs: 'Detailed explanation of the concept.',
useWhen: [
'First use case',
'Second use case',
],
prevents: 'What problem/failure this prevents',
combineWith: ['Other Primitive', 'Another Primitive'],
implementations: [
{
provider: 'copilot',
implementation: 'How Copilot implements this',
location: '.github/path/to/file',
support: 'full', // 'full' | 'partial' | 'diy'
sourceUrl: 'https://docs.github.com/...', // primary provider documentation
},
{
provider: 'claude',
implementation: 'How Claude implements this',
location: '.claude/path/to/file',
support: 'full',
sourceUrl: 'https://code.claude.com/docs/...',
},
{
provider: 'cursor',
implementation: 'How Cursor implements this',
location: '.cursor/path/to/file',
support: 'full',
sourceUrl: 'https://cursor.com/docs/...',
},
{
provider: 'codex',
implementation: 'How Codex implements this',
location: '~/.codex/path/to/file',
support: 'full',
sourceUrl: 'https://developers.openai.com/codex/...',
},
],
category: 'instructions', // one of the 8 layer ids — see Categories below
}
Always list all four providers (copilot, claude, cursor, codex) even when support is partial or diy — a missing provider entry silently reads as "no data" rather than "not supported," which the refresh-provider-docs skill and comparison table both rely on to stay honest. Cite a primary sourceUrl for every claim; do not add a primitive with unverified provider claims (use the refresh-provider-docs skill first if you have not already confirmed the paths against current documentation).
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 · 175 lines · 35 tokens per session scan A 33c02e45d7c0
add-primitive is a skill published in the GitHub repository agentconfig/agentconfig.org (8 stars, last pushed 7d ago), licensed ISC. It adds 35 tokens to every session and 1,897 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
clinical-decision-support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading…
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.
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.
immunology-assays
Computational analysis of immunology experimental data. ATAC-seq differential accessibility, immune cell tracking from microscopy, ELISA data processing with 4-parameter logistic fitting, immunohistochemistry quantification, antibody titer analysis, and cell cycle phase duration estimation. For flow cytometry use…
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.