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/retyc/retyc-cli/claude-mdgit clone --depth 1 https://github.com/retyc/retyc-cliWrote 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/retyc/retyc-cli/claude-md)<a href="https://agentmods.dev/instructions/retyc/retyc-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/retyc/retyc-cli/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 | $0.04191 | $0.04191 |
| Opus 5 | $0.02096 | $0.02096 |
| Sonnet 5 | $0.00838 | $0.00838 |
| Haiku 4.5 | $0.00419 | $0.00419 |
Grade A, and why
retyc-cli 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.
How it starts
The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — retyc-cli
Project
Go CLI for the RETYC platform. Module: github.com/retyc/retyc-cli
Structure
main.go # Entry point — calls cmd.Execute()
cmd/
root.go # cobra root, --config / --insecure / --debug flags, viper init
auth.go # auth login / logout / status + newHTTPClient + debugTransport
common.go # Shared helpers: constants, newAPIClient, resolveUserIdentity,
# newTransferBar, uploadChunks, downloadChunks
transfer.go # transfer ls/info/create/download/enable/disable
dataroom.go # dataroom commands (ls, cp, mv, rm, mkdir, create, info, user)
mcp.go # mcp serve (stdio MCP server) + tool registry
mcp_manifest.go # mcp manifest — full MCPB manifest.json (version + tools injected)
mcpb_manifest_base.json # static MCPB manifest metadata (go:embed into mcp_manifest.go)
version.go # version command (shows version + build mode)
internal/
auth/oidc.go # DeviceFlow, Refresh, GetValidToken
api/
client.go # Authenticated REST client (oauth2 transport)
# Get, Post, Put, Patch, Delete, PostMultipartChunk, GetBytes
login.go # FetchOIDCConfig (unauthenticated, GET /login/config/public)
transfer.go # Transfer types + ListTransfers, GetTransferDetails,
# ListFiles, CreateShare, CreateFile, UploadChunk,
# CompleteTransfer, DisableTransfer, EnableTransfer
dataroom.go # Dataroom types + all dataroom API methods
user.go # UserKey type + GetActiveKey
config/
config.go # Structs, SetDefaults(), Load(), token persistence
paths_dev.go # configDir() + defaultAPIBaseURL for dev
paths_prod.go # configDir() + defaultAPIBaseURL for prod
crypto/age.go # AGE encrypt/decrypt helpers (PQ-only, see below)
keyring/keyring.go # Linux kernel session keyring cache (TTL-based)
mcpb/icon.png # MCPB bundle icon (512×512)
scripts/build-mcpb.sh # Builds dist/retyc-<version>.mcpb from goreleaser dist/ (jq+zip, no Node)
Dockerfile # Multi-stage scratch image (golang:1.24 builder → scratch)
.dockerignore
.github/workflows/ci.yml # CI + release workflow
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 · 325 lines · 4,191 tokens per session scan A 46f353e186d6
retyc-cli CLAUDE.md is an instructions file published in the GitHub repository retyc/retyc-cli (22 stars, last pushed 1mo ago), licensed MIT. It adds 4,191 tokens to every session, about $0.0210 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
plik AGENTS.md
AGENTS.md instructions for root-gg/plik, covering agents.md — plik, what is plik?, tech stack, repo layout and build & run.
homebutler CLAUDE.md
Claude Code instructions for Higangssh/homebutler, covering homebutler, verify before claiming anything works, writing commits, prs, and comments, no tool attribution and commit subjects.
vnsh CLAUDE.md
Instructions for raullenchai/vnsh, covering vnsh contributor context, current product model, repository, development and deployment and security invariants.
vnsh AGENTS.md
Instructions for raullenchai/vnsh: Read the nearest nested AGENTS.md before editing a package.
GoDrop CLAUDE.md
Claude Code instructions for fatihbaltaci/GoDrop, covering claude.md, commands, what ci enforces, generated files: never edit by hand and architecture.
DirForge CLAUDE.md
Instructions for Dissimilis/DirForge, covering claude.md, project, philosophy, 1) security before features and 2) read-only means read-only.