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 instructions/mr-kelly/skills/agents-mdgit clone --depth 1 https://github.com/mr-kelly/skillsWrote 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/instructions/mr-kelly/skills/agents-md)<a href="https://agentmods.dev/instructions/mr-kelly/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/mr-kelly/skills/agents-md.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 | $0.01803 | $0.01803 |
| Opus 5 | $0.00901 | $0.00901 |
| Sonnet 5 | $0.00361 | $0.00361 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
skills AGENTS.md 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 5d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Kelly's App-in-Skill workspace: 67 skills under skills/, each pairing an agent operating
procedure with a Busabase-backed local browser UI for human review and approval.
Skill taxonomy
Every skill declares its own classification in SKILL.md frontmatter. That frontmatter is the
single source of truth — the site sections, the site filters, the README tables, and the
marketplace tags are all derived from it. Nothing is maintained in a second list.
---
name: kelly-retail-intel
description: ...
metadata:
category: industry-intel
tags:
- risk:gated-write
- industry:retail
- surface:busabase
---
Put this under metadata:, not as top-level category: / tags: keys. gh skill publish
validates frontmatter against the agentskills.io spec and one bad skill blocks the whole release;
metadata is the spec's free-form field (--fix only strips metadata.github-* install
metadata, leaving other subkeys alone). Top-level custom keys have no such guarantee.
category — required, exactly one
One of these thirteen. They are mutually exclusive and decide which section a skill appears in.
Defined in scripts/lib/skill-taxonomy.mjs.
| id | Section | Who it serves |
|---|---|---|
finance |
Finance & Back Office | money, ledgers, invoices, reconciliation |
invest |
Investing & Wealth | personal and family holdings |
rbf |
Revenue-Based Finance | RBF / private-credit fund workflows |
legal |
Legal & Contracts | law firms and in-house legal |
sales-crm |
Sales & Customer | sales, support, customer success |
comms |
Comms & Team | inboxes and team boards |
marketing |
Brand & Marketing | brand, content, launches |
growth |
Growth & Analytics | search, competitors, behaviour data |
ecommerce |
Cross-Border E-commerce | sourcing → listing → ads |
industry-intel |
Industry Intelligence | per-vertical daily intelligence cockpits |
production |
Production | video, decks, digital humans |
education |
Education & Teaching | deans, teachers, parents |
platform |
Agent & Dev Platform | building skills, running agents, ops |
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.
- 5d ago First seen · 143 lines · 1,803 tokens per session scan A 686f49b8e5fa
skills AGENTS.md is an instructions file published in the GitHub repository mr-kelly/skills (5 stars, last pushed yesterday), licensed MIT. It adds 1,803 tokens to every session, about $0.0090 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 instructions, from other repositories
slide-sage AGENTS.md
Instructions for rhnfzl/slide-sage, covering slide sage - ai presentation skill, quick start, what this skill does, workflow and intake rule.
vast-cli CLAUDE.md
Claude Code instructions for vast-ai/vast-cli, covering vast-ai/vast-cli and ai agents.
supergraph AGENTS.md
AGENTS.md instructions for datit309/supergraph, covering supergraph — mandatory workflows, skills, auto language detection, tiered workflow — pick the right tier first and full pipeline (tier 3).
mobile-ai-agents CLAUDE.md
Claude Code instructions for salmanashraf/mobile-ai-agents, covering claude.md — mobile ai agents, what this repo is, quick start, install everything and install by platform.
MemoryCustodian GEMINI.md
Gemini CLI instructions for waittim/MemoryCustodian, covering agent instructions, memorycustodian and development.
dining-places-skill AGENTS.md
AGENTS.md instructions for ddalgrande/dining-places-skill, covering agents.md, how to use it, by agent capability, the one command and ground rules.