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/ldclabs/cose/agents-mdgit clone --depth 1 https://github.com/ldclabs/coseWhat 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 | $0.01386 | $0.01386 |
| Opus 5 | $0.00693 | $0.00693 |
| Sonnet 5 | $0.00277 | $0.00277 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade A, and why
cose 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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide for github.com/ldclabs/cose
This repository is a Go module for COSE, CWT, COSE keys, and IANA constants. When generating code against this module, prefer the public package APIs over hand-built CBOR arrays or maps.
Package Map
github.com/ldclabs/cose/cose: COSE message types and encode/decode helpers.github.com/ldclabs/cose/cwt: CWT claim structs and validators.github.com/ldclabs/cose/key: COSE key model, registry, CBOR helpers, and crypto interfaces.github.com/ldclabs/cose/iana: IANA labels, algorithms, curves, operations, and tags.github.com/ldclabs/cose/key/all: opt-in aggregate import for built-in algorithm packages.
Algorithm Registration
The key.Key.Signer, Verifier, MACer, and Encryptor methods use the
registry in key. Import the concrete algorithm package before calling them.
For generated applications and examples, this is the least surprising default:
import _ "github.com/ldclabs/cose/key/all"
For library code, prefer importing only the concrete algorithms actually needed, for example:
import (
"github.com/ldclabs/cose/key/ed25519"
_ "github.com/ldclabs/cose/key/aesgcm"
)
If an error contains is not registered, add the matching algorithm package or
the aggregate key/all import. Do not work around it by bypassing the registry.
Key Construction
Prefer the per-package GenerateKey constructors over hand-built key maps. They
set the correct kty, crv, alg, and key-bytes for you, so an agent never has
to guess IANA label combinations:
| Use case | Constructor | Algorithm argument (from iana) |
|---|---|---|
| EdDSA signing | ed25519.GenerateKey() |
none |
| ECDSA signing | ecdsa.GenerateKey(alg) |
AlgorithmES256, AlgorithmES384, AlgorithmES512 |
| ECDH agreement | ecdh.GenerateKey(crv) |
EllipticCurveP_256/P_384/P_521, EllipticCurveX25519 |
| AES-GCM encrypt | aesgcm.GenerateKey(alg) |
AlgorithmA128GCM, AlgorithmA192GCM, AlgorithmA256GCM |
| AES-CCM encrypt | aesccm.GenerateKey(alg) |
AlgorithmAES_CCM_* |
| ChaCha20/Poly1305 | chacha20poly1305.GenerateKey() |
none |
| HMAC | hmac.GenerateKey(alg) |
AlgorithmHMAC_256_64/256_256/384_384/512_512 |
| AES-CBC-MAC | aesmac.GenerateKey(alg) |
AlgorithmAES_MAC_* |
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 · 117 lines · 1,386 tokens per session scan A bd91d1029aad
cose AGENTS.md is an instructions file published in the GitHub repository ldclabs/cose (24 stars, last pushed 1mo ago), licensed MIT. It adds 1,386 tokens to every session, about $0.0069 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.