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/datazoode/triton/claude-mdgit clone --depth 1 https://github.com/DataZooDE/tritonWrote 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/datazoode/triton/claude-md)<a href="https://agentmods.dev/instructions/datazoode/triton/claude-md"><img src="https://agentmods.dev/badge/instructions/datazoode/triton/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 | $0.02009 | $0.02009 |
| Opus 5 | $0.01005 | $0.01005 |
| Sonnet 5 | $0.00402 | $0.00402 |
| Haiku 4.5 | $0.00201 | $0.00201 |
Grade A, and why
triton 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 4d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 4d ago First seen · 146 lines · 2,009 tokens per session scan A 649136e19d48
triton CLAUDE.md is an instructions file published in the GitHub repository DataZooDE/triton (2 stars, last pushed 4d ago), with no licence file. It adds 2,009 tokens to every session, about $0.0100 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
codex-a2a-gateway AGENTS.md
AGENTS.md instructions for phamviet86/codex-a2a-gateway, covering repository guidance, mission and scope, architecture ownership, non-negotiable invariants and compatibility policy.
awaken CLAUDE.md
Claude Code instructions for awakenworks/awaken, covering core rules, pre-implementation checks, implementation cycle (per section), completion notes and planning & discussion rules.
awaken AGENTS.md
AGENTS.md instructions for awakenworks/awaken, a project described as: AI agent runtime for Rust — type-safe state, multi-protocol serving, plugin extensibility.
a2a CLAUDE.md
Claude Code instructions for mirni/a2a, covering development workflow: test-driven development (tdd), 1. red phase (failing test), 2. green phase (pass test), 3. refactor phase (clean up) and git/github workflow: feature branch model.
arc AGENTS.md
AGENTS.md instructions for howells/arc, covering arc, shape, gotchas, editing constraints and search order.
idd-skill idd-resume.instructions.md
Instructions for kurone-kito/idd-skill, covering idd — resume phase, required inputs, step 0 — route classifier, operator-present release and step 1 — identify claim state.