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/jmagly/kintsugi-usb/agents-mdgit clone --depth 1 https://github.com/jmagly/kintsugi-usbWhat 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 | $0.00695 | $0.00695 |
| Opus 5 | $0.00347 | $0.00347 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
kintsugi-usb 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 2d 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.
- 2d ago First seen · 58 lines · 695 tokens per session scan A 5912320bb6fd
kintsugi-usb AGENTS.md is an instructions file published in the GitHub repository jmagly/kintsugi-usb (11 stars, last pushed 1mo ago), with no licence file. It adds 695 tokens to every session, about $0.0035 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
mdevolved AGENTS.md
AGENTS.md instructions for msinclair25/mdevolved, covering mdevolved agent instructions, mission, instruction precedence, non-negotiable product boundaries and repository shape.
Build26-BRK228-modern-resiliency-from-build-to-recovery-through-agentic-ai AGENTS.md
Instructions for microsoft/Build26-BRK228-modern-resiliency-from-build-to-recovery-through-agentic-ai, covering ai agent guidelines, 🔒 security best practices, 📋 repository guidelines, purpose and what not to modify without permission.
Build26-BRK228-modern-resiliency-from-build-to-recovery-through-agentic-ai copilot-instructions.md
Instructions for microsoft/Build26-BRK228-modern-resiliency-from-build-to-recovery-through-agentic-ai: This is a Microsoft Build 2026 session content repository.
ii-agent AGENTS.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
nimbalyst AGENTS.md
AGENTS.md instructions for nimbalyst/nimbalyst: At the beginning of every AI session, read the root CLAUDE.md and any applicable package-level CLAUDE.md before taking actions.