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 skills/eigenwise/eigenwise-toolshed/enable-project-telemetrynpx skills add Eigenwise/eigenwise-toolshed --skill enable-project-telemetrygit clone --depth 1 https://github.com/Eigenwise/eigenwise-toolshedWrote 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/skills/eigenwise/eigenwise-toolshed/enable-project-telemetry)<a href="https://agentmods.dev/skills/eigenwise/eigenwise-toolshed/enable-project-telemetry"><img src="https://agentmods.dev/badge/skills/eigenwise/eigenwise-toolshed/enable-project-telemetry.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 | $0.00033 | $0.01314 |
| Opus 5 | $0.00016 | $0.00657 |
| Sonnet 5 | $0.00007 | $0.00263 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
enable-project-telemetry 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enable Project Telemetry
Telemetry is opt-in per repository. A project is its enclosing git repository, so every working directory inside it (subdirectories, linked worktrees) reports under the repository's identity and lands on one dashboard. Never write user-scope settings and never enable it for a different project. The local registry only includes repositories that explicitly opted in, so dashboard work can exclude every other project.
Claude Code reads OTEL_RESOURCE_ATTRIBUTES from the settings of the directory a session started in and does
not walk up to the repository root. That is why the enable command writes the env into the repository root
and into each subdirectory that has hosted Claude Code sessions, all carrying the repository's
project.id. Hook-based observer data needs none of that: it is repository-rooted from the first event.
Read setup-reference.md before the first enable on a machine. It owns the consent question, the
setup-observability.js commands that install the pinned Collector and choose a sink, dashboard, and ports,
and the deletion rules. Do the setup pass first, then the per-project wiring below.
Enable
Gateway wiring is per-scope. If the gateway is unwired for the current project, invoke /model-gateway:model-gateway and use its env --write-project command to wire this project. Use env --write-user only when machine-wide wiring is wanted. Do not invoke a bare codex-gateway shell command, since the installed plugin command is not on PATH.
- Confirm the user wants local, metadata-only usage telemetry for the current repository. Say it writes only
this repository's own
.claude/settings.local.jsonfiles, then sends metadata through the local loopback observer and Collector to local Grafana: API-equivalent cost; input, output, and cache token totals; tool-call names, counts, and result-token estimates; and model, session, agent, and activity information. It does not capture prompt or response text, code or file contents, tool inputs or results, raw request bodies, credentials, or environment values. - Run it from anywhere inside the repository; it resolves the repository root itself:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 88 lines · 33 tokens per session scan A 09c4132bda59
enable-project-telemetry is a skill published in the GitHub repository Eigenwise/eigenwise-toolshed (37 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 1,314 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…