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/mizune/llm-cli-telemetry/claude-mdgit clone --depth 1 https://github.com/Mizune/llm-cli-telemetryWrote 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/mizune/llm-cli-telemetry/claude-md)<a href="https://agentmods.dev/instructions/mizune/llm-cli-telemetry/claude-md"><img src="https://agentmods.dev/badge/instructions/mizune/llm-cli-telemetry/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 | $0.01192 | $0.01192 |
| Opus 5 | $0.00596 | $0.00596 |
| Sonnet 5 | $0.00238 | $0.00238 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade B, and why
llm-cli-telemetry CLAUDE.md scanned grade B with 2 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 3d 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.
- **Codex CLI** OTEL is configured via `~/.codex/config.toml` `[otel]` section (set by install.sh). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **OTEL Collector image** (`otel/opentelemetry-collector-contrib`) is distroless: no shell, wget, or curl. Healthcheck is disabled in compose; use `./status.sh` (external curl) instead. How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
llm-cli-telemetry
Project Overview
Telemetry collection stack for Claude Code, Codex CLI, and Gemini CLI via shell function wrappers. Supports two modes: local (Docker Compose stack with Prometheus/Loki/Tempo/Grafana) and remote (direct OTLP export to any endpoint, no Docker required). Data flows through OTEL Collector or directly to remote endpoints.
Architecture
- Shell functions wrap
claude/codex/geminicommands, injecting OTEL env vars transparently telemetry.yamldrives all configuration;scripts/generate.shproduces collector config and compose overrides (local mode only)- Data collection: automatic OTEL export + optional local log file ingestion via filelog receiver
- Env var prefix:
LLM_CLI_TELEMETRY_* .setup-modefile stores current mode/protocol/endpoint/headers (pipe-delimited)
Key Files
| File | Purpose |
|---|---|
setup.sh |
Entry point: interactive setup (calls scripts/install.sh) |
start.sh |
Start local Docker stack with auto-generate |
stop.sh |
Stop Docker services (--clean for volumes) |
status.sh |
Mode-aware health check |
uninstall.sh |
Entry point: remove integration (calls scripts/uninstall.sh) |
scripts/lib.sh |
Shared utilities: logging, .setup-mode readers, common variables |
scripts/shell-integration.sh |
Shell functions (claude/codex/gemini) with OTEL env vars |
scripts/install.sh |
Interactive setup: mode selection, prerequisites, CLI configs |
scripts/uninstall.sh |
Remove shell integration, restore configs from .bak |
scripts/generate.sh |
telemetry.yaml -> collector-config.yaml + docker-compose.override.yml |
.env.example |
Environment variables template (Grafana creds, OTEL endpoint) |
.setup-mode |
Generated: setup state (mode|protocol|endpoint|headers) |
telemetry.example.yaml |
User config template (copied to telemetry.yaml on install) |
otel-collector/collector-config.yaml |
Generated OTEL Collector pipeline config |
docker-compose.yml |
Service definitions (collector, prometheus, loki, tempo, grafana) |
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.
- 3d ago First seen · 91 lines · 1,192 tokens per session scan B ac35013f0578
llm-cli-telemetry CLAUDE.md is an instructions file published in the GitHub repository Mizune/llm-cli-telemetry (3 stars, last pushed 4mo ago), licensed MIT. It adds 1,192 tokens to every session, about $0.0060 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
ai-observer CLAUDE.md
Instructions for tobilg/ai-observer, covering claude.md, project overview, build & development commands, setup and development.
opensre AGENTS.md
AGENTS.md instructions for Tracer-Cloud/opensre, covering opensre development reference, ci failures and tests (mandatory — every pr / push), build and run commands, code style and tests (high-signal, not exhaustive).
obsidian-mind CLAUDE.md
Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.
openllmetry CLAUDE.md
Instructions for traceloop/openllmetry, covering openllmetry repository guide, repository structure, nx workspace commands, run tests across all packages and run linting across all packages.
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
Instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.