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/tobilg/ai-observer/claude-mdgit clone --depth 1 https://github.com/tobilg/ai-observerWrote 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/tobilg/ai-observer/claude-md)<a href="https://agentmods.dev/instructions/tobilg/ai-observer/claude-md"><img src="https://agentmods.dev/badge/instructions/tobilg/ai-observer/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 | $0.03189 | $0.03189 |
| Opus 5 | $0.01595 | $0.01595 |
| Sonnet 5 | $0.00638 | $0.00638 |
| Haiku 4.5 | $0.00319 | $0.00319 |
Grade B, and why
ai-observer CLAUDE.md scanned grade B 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
# Gemini CLI - add to ~/.gemini/settings.json How it starts
The opening of the file, as written. The whole thing — 303 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 Overview
AI Observer is an OpenTelemetry-compatible observability backend designed for monitoring AI coding tools (Claude Code, OpenAI Codex CLI, Gemini CLI). It provides real-time ingestion of OTLP traces, metrics, and logs with a DuckDB-based storage layer and a React dashboard.
Build & Development Commands
# Setup
make setup # Install all dependencies (go mod download + pnpm install)
# Development
make dev # Run both backend and frontend in dev mode (parallel)
make backend-dev # Run only backend (go run ./cmd/server)
make frontend-dev # Run only frontend (pnpm dev at localhost:5173)
# Build
make all # Build both backend and frontend
make backend # Build backend binary to bin/ai-observer
make frontend # Build frontend for production
# Testing
make test # Run all tests
make backend-test # Run Go tests: cd backend && go test -v ./...
make frontend-test # Run frontend tests: cd frontend && pnpm test
# Run a single Go test
cd backend && go test -v -run TestFunctionName ./path/to/package
# Run a single frontend test
cd frontend && pnpm vitest run src/path/to/file.test.ts
# Linting
make lint # Run all linters
make backend-lint # Run golangci-lint
make frontend-lint # Run ESLint
# Cleanup
make clean # Remove bin/ and frontend/dist/
Architecture
Backend (Go)
The backend runs two HTTP servers simultaneously:
-
OTLP Ingestion Server (port 4318) - Receives telemetry from AI tools
POST /v1/traces- Trace data (protobuf or JSON)POST /v1/metrics- Metrics dataPOST /v1/logs- Log data- Supports HTTP/1.1 + h2c (HTTP/2 cleartext), gzip-compressed payloads
- Auto-detects JSON vs Protobuf format regardless of Content-Type header
-
API/WebSocket Server (port 8080) - Serves dashboard and real-time updates
/api/traces,/api/metrics,/api/logs- Query endpoints/api/services,/api/stats- Aggregations/api/dashboards- Dashboard CRUD/ws- WebSocket for real-time updates to frontend- Serves embedded React frontend at root
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 · 303 lines · 3,189 tokens per session scan B e639fbbb70ea
ai-observer CLAUDE.md is an instructions file published in the GitHub repository tobilg/ai-observer (272 stars, last pushed 2mo ago), licensed MIT. It adds 3,189 tokens to every session, about $0.0159 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
llm-cli-telemetry CLAUDE.md
Instructions for Mizune/llm-cli-telemetry, covering llm-cli-telemetry, project overview, architecture, key files and commands.
obsidian-mind CLAUDE.md
Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.
obsidian-mind AGENTS.md
AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.
parallel-code CLAUDE.md
Claude Code instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.
neo4j-skills AGENTS.md
AGENTS.md instructions for neo4j-contrib/neo4j-skills, covering writing skills for this repository, language style — write for agents, not humans, six design principles, skill.md spec (agentskills.io) and frontmatter.
ox AGENTS.md
AGENTS.md instructions for sageox/ox, covering human attention is the scarcest resource, what is ox?, quick start, terminology and required reviews.