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/pug-sh/pug/claude-mdgit clone --depth 1 https://github.com/pug-sh/pugWrote 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/pug-sh/pug/claude-md)<a href="https://agentmods.dev/instructions/pug-sh/pug/claude-md"><img src="https://agentmods.dev/badge/instructions/pug-sh/pug/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 | $0.12270 | $0.12270 |
| Opus 5 | $0.06135 | $0.06135 |
| Sonnet 5 | $0.02454 | $0.02454 |
| Haiku 4.5 | $0.01227 | $0.01227 |
Grade A, and why
pug CLAUDE.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 yesterday.
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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- yesterday Changed · +69 tokens per session cf6f6a1f1fa7
- 5d ago First seen · 281 lines · 12,201 tokens per session scan A 7a9171380336
pug CLAUDE.md is an instructions file published in the GitHub repository pug-sh/pug (56 stars, last pushed yesterday), with no licence file. It adds 12,270 tokens to every session, about $0.0614 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
jitsu AGENTS.md
AGENTS.md instructions for jitsucom/jitsu, covering jitsu — agent guidelines, project overview, repository structure, go (/bulker) and node.js / typescript.
phpClickHouse CLAUDE.md
Instructions for smi2/phpClickHouse, covering claude.md — phpclickhouse, project overview, principles, architecture and key notes.
clickhouse-sql-parser AGENTS.md
AGENTS.md instructions for AfterShip/clickhouse-sql-parser, covering ai agents guidline, development commands, build the cli binary, run tests and update golden fixtures after intentional output changes.
clickhouse-sql-parser CLAUDE.md
Claude Code instructions for AfterShip/clickhouse-sql-parser, a project described as: Go library and CLI that parses ClickHouse-dialect SQL into a typed AST. Supports lexing, parsing, AST walking, round-trip formatting, and beautification. Use for query linting, static analysis, rewriting, access-control enforcement…
datapages CLAUDE.md
Claude Code instructions for romshark/datapages, a project described as: A Datastar Go web frontend framework.
dingtalk-workspace-cli AGENTS.md
AGENTS.md instructions for DingTalk-Real-AI/dingtalk-workspace-cli, covering repository agent guide, build and test, command framework declaration, flag / help / schema homology and agent schema contract.