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/itsab1989/chromiq/claude-mdgit clone --depth 1 https://github.com/itsab1989/ChromIQWrote 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/itsab1989/chromiq/claude-md)<a href="https://agentmods.dev/instructions/itsab1989/chromiq/claude-md"><img src="https://agentmods.dev/badge/instructions/itsab1989/chromiq/claude-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 | $0.06729 | $0.06729 |
| Opus 5 | $0.03365 | $0.03365 |
| Sonnet 5 | $0.01346 | $0.01346 |
| Haiku 4.5 | $0.00673 | $0.00673 |
Grade A, and why
ChromIQ CLAUDE.md 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 today.
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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`subprocess.run` without one waits for ever, and `targen -G` can wedge: the The source is not reproduced here
Licensed GPL-3.0
The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- today Changed · +138 lines · +2,161 tokens per session 4dfa8760b3d3
- 6d ago First seen · 353 lines · 4,568 tokens per session scan A 11e35ba39943
ChromIQ CLAUDE.md is an instructions file published in the GitHub repository itsab1989/ChromIQ (21 stars, last pushed today), licensed GPL-3.0. It adds 6,729 tokens to every session, about $0.0336 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
mathmodel-skill AGENTS.md
Instructions for handsomeZR-netizen/mathmodel-skill, covering repository instructions, sources of truth, maintenance rules and verification.
usd-routing-coach-ar AGENTS.md
Instructions for Nicopatron/usd-routing-coach-ar, covering agents.md, files to read on first paste, in this order, default workflow on every paste, runtime contracts (canonical in rules.md) and precedence when instructions conflict.
maryslab CLAUDE.md
Claude Code instructions for JeetuSK0808/maryslab, covering mary's lab — agent onboarding, layout, build & test commands, mcp (works on this machine — no c++ toolchain needed) and data pipeline.
taurus CLAUDE.md
Claude Code instructions for astetic-dev/taurus, covering taurus — project instructions, contribution workflow — changes go through github issues and stack.
icm-spec AGENTS.md
AGENTS.md instructions for andyrids/icm-spec, covering icm-spec plugin, context hierarchy, frontmatter, design principles and stage contracts and handoffs.
usd-routing-coach-ar CLAUDE.md
Instructions for Nicopatron/usd-routing-coach-ar: This project uses the agent-neutral AGENTS.md convention. See AGENTS.md for the operational primer.