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/carlosprados/og-cli/claude-mdgit clone --depth 1 https://github.com/carlosprados/og-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/carlosprados/og-cli/claude-md)<a href="https://agentmods.dev/instructions/carlosprados/og-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/carlosprados/og-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 | $0.02680 | $0.02680 |
| Opus 5 | $0.01340 | $0.01340 |
| Sonnet 5 | $0.00536 | $0.00536 |
| Haiku 4.5 | $0.00268 | $0.00268 |
Grade A, and why
og-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 5d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project
og is a CLI tool (binary name: og) for the OpenGate IoT platform REST API by Amplía Soluciones. Built in Go with Cobra (commands), Viper (config), and Bubble Tea + Lip Gloss (interactive TUI).
Commands
task build # build the og binary
task test # go test ./... -v
task lint # golangci-lint run ./...
task fmt # gofmt + goimports
task tidy # go mod tidy
task install # go install with ldflags
go test ./internal/client/ -run TestLogin -v # run a single test
Version info is injected via ldflags — see Taskfile.yml LDFLAGS.
Architecture
main.go → cmd.Execute()
cmd/ → Cobra commands (root, login, version, mcp, datamodels, devices)
pkg/opengate/ → OpenGate REST API client (HTTP methods, auth, resource methods)
pkg/query/ → Search filter parser (-w "field op value", query strings)
internal/config/ → Viper config, profiles, .env loading
internal/mcp/ → MCP server (stdio + HTTP transports) + tool definitions
internal/output/ → JSON/table output formatting
internal/tui/ → Bubble Tea interactive TUI
internal/unwrap/ → Workspace/rule/connector unwrap to local dirs
internal/views/ → Named field views for searches
pkg/ is the public library surface: it is consumed by external services (e.g.
Punto de Luz), so its API is a contract. internal/ is CLI-private.
Library conventions for pkg/:
- Every method that performs I/O takes
ctx context.Contextas its first parameter, propagated tohttp.NewRequestWithContext. No exceptions. - Per-client configuration goes through functional options on
New(WithHTTPClient,WithTLS,WithAPIVersion,WithAPIKey) — never process-wide state.ConfigureTLS/NewHTTPClientare deprecated leftovers kept for the CLI, which has exactly one endpoint per invocation. - North API path constants carry the
{v}version placeholder, resolved per client. Never hardcode a version segment. - A misconfigured client is not a panic and not a second constructor:
Newrecords the error, andErr()plus every request return it.
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.
- 5d ago First seen · 191 lines · 2,680 tokens per session scan A ee4236b439f4
og-cli CLAUDE.md is an instructions file published in the GitHub repository carlosprados/og-cli (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 2,680 tokens to every session, about $0.0134 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
dingtalk-workspace-cli AGENTS.md
AGENTS.md instructions for DingTalk-Real-AI/dingtalk-workspace-cli, covering repository agent guide, build and test, command framework declaration, flag / help / schema homology and agent schema contract.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
unraid-management-agent copilot-instructions.md
Copilot instructions for ruaan-deysel/unraid-management-agent, covering copilot instructions, copilot workflow, path-specific instructions, reusable prompts and quick commands.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
agentcat-go-sdk CLAUDE.md
Claude Code instructions for agentcathq/agentcat-go-sdk, covering claude.md, what this is, build & test commands, module layout and architecture.
oastools GEMINI.md
Instructions for erraggy/oastools, covering gemini.md, project overview, building and running, key commands and development conventions.