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/catalystbyzoho/agent-skills/agents-mdgit clone --depth 1 https://github.com/catalystbyzoho/agent-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/catalystbyzoho/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/catalystbyzoho/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/catalystbyzoho/agent-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 | $0.01602 | $0.01602 |
| Opus 5 | $0.00801 | $0.00801 |
| Sonnet 5 | $0.00320 | $0.00320 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade A, and why
agent-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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributing to catalyst-skills
This guide explains how to create, extend, and maintain agent skills for Catalyst by Zoho. Read this before submitting a PR.
Repository layout
skills/
SKILL.md ← routing layer (do not add technical content here)
{catalyst-service}/
SKILL.md ← thin entry point: frontmatter + workflow + triggers + references table
references/
{topic}.md ← detailed technical content loaded on demand
The routing catalyst-by-zoho/SKILL.md routes queries to service-level skills. Service skills route to reference files. Never inline detailed technical content in a SKILL.md — it gets loaded on every match and bloats the context window.
How Skills Load (3-Tier Model)
Every agent interaction with skills goes through three loading stages:
| Tier | What loads | When |
|---|---|---|
| 1 — Metadata | YAML frontmatter only (name, description, metadata) |
Always — for every skill in the registry, on every request |
| 2 — Body | Full SKILL.md markdown (How It Works, Triggers, Security Checklist, References table) | Only when the skill's description matches the user query |
| 3 — References | Individual references/*.md files |
Only when a step in How It Works explicitly loads one |
Critical implication: The description field is the ONLY content available at routing time. Every product name, symptom phrase, error term, and common entry point that should trigger this skill MUST appear in the description. The ## Triggers section in the body is the fallback for agents that read the full SKILL.md, but it does not help with initial routing.
Do not put trigger context only in the body. If a user asks about busboy and busboy is not in the description, the skill won't trigger — even if it's in ## Triggers.
SKILL.md format
Every skills/{service}/SKILL.md must follow this structure exactly:
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 · 151 lines · 1,602 tokens per session scan A 1c235374189e
agent-skills AGENTS.md is an instructions file published in the GitHub repository catalystbyzoho/agent-skills (57 stars, last pushed 7d ago), licensed Apache-2.0. It adds 1,602 tokens to every session, about $0.0080 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.