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/wraps-team/wraps/agents-mdgit clone --depth 1 https://github.com/wraps-team/wrapsWhat 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 | $0.04231 | $0.04231 |
| Opus 5 | $0.02116 | $0.02116 |
| Sonnet 5 | $0.00846 | $0.00846 |
| Haiku 4.5 | $0.00423 | $0.00423 |
Grade C, and why
wraps AGENTS.md scanned grade C 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 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
// Resolves: env vars -> ~/.aws/credentials -> IAM role 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 · 621 lines · 4,231 tokens per session scan C 533e147709fa
wraps AGENTS.md is an instructions file published in the GitHub repository wraps-team/wraps (56 stars, last pushed 3d ago), with no licence file. It adds 4,231 tokens to every session, about $0.0212 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
nx-plugin-for-aws CLAUDE.md
Instructions for awslabs/nx-plugin-for-aws, covering instructions for claude, required reading, commands, tips and code style.
job-search-agent AGENTS.md
Instructions for deeheber/job-search-agent, covering job search agent and conventions.
mcp-hey CLAUDE.md
Instructions for Sealjay/mcp-hey, covering hey.com mcp server, architecture, tech stack, commands and development workflow.
infrawise AGENTS.md
Instructions for Sidd27/infrawise, covering infrawise — ai instructions, project goal, pre-release checklist — no exceptions, releasing to the mcp registry and standing rules.
hail CLAUDE.md
Claude Code instructions for hail-hq/hail, covering claude.md, what hail is, repo layout, tenets and invariants.
aws-s3-mcp CLAUDE.md
Instructions for samuraikun/aws-s3-mcp, covering claude.md, common development commands, building and running, testing and code quality.