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 skills add flurdy/agent-skills --skill watch-telemetrygit clone --depth 1 https://github.com/flurdy/agent-skillsWrote 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/flurdy/agent-skills/watch-telemetry)<a href="https://agentmods.dev/skills/flurdy/agent-skills/watch-telemetry"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/watch-telemetry/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/flurdy/agent-skills/watch-telemetry"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/watch-telemetry.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00037 | $0.01722 |
| Opus 5.5 | $0.00015 | $0.00689 |
| Sonnet 5.5 | $0.00007 | $0.00344 |
| Haiku 4.5 | $0.00004 | $0.00172 |
Grade A, and why
watch-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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watcher Execution Counts
One local counter authority for the seven watch-* entry points. These are agent-reported
execution observations, always partial: not scheduler dispatch, unique runs, successful work,
or evidence that a watcher is safe to retire. Do not read native transcripts to fill gaps.
Usage
/watch-telemetry # counts for the last 90 UTC days, including today
/watch-telemetry counts --days 7
/watch-telemetry enable # explicitly opt in on this machine
/watch-telemetry disable # stop collection; retain recent counters
/watch-telemetry prune # remove expired counter/configuration-day buckets
Requires Python 3.10+ on Unix with fcntl, directory-relative file operations, and a local
filesystem supporting advisory locks and atomic rename. No packages, network, credentials,
repository inspection, or runtime extension are needed. Missing support means unavailable;
never install dependencies or modify another workflow to make telemetry work.
Query
With no arguments use counts --days 90. Accept only the forms above; days must be 1–90.
~/.agents/skills/watch-telemetry/scripts/watch_telemetry.py counts --days 90
Render the returned UTC window and one compact table: watcher, harness, invocations, ticks.
watch-rollout selects a specialist and has no ticks: render its null tick count as —, not zero.
An invocation of the dispatcher followed by its specialist intentionally appears under both names;
do not sum those rows as unique watches.
Always show source: agent-reported; coverage: partial for an existing store. Configuration-day
counts (enabled, disabled, mixed, unknown) describe the configured policy, not successful
instrumentation coverage. A missing store is disabled/unavailable with no numeric rows; an unsafe,
malformed, locked, or unreadable store is unavailable, not empty success. Do not repair it here.
Zero observations are not proof of zero use. Collection is disabled by default; other machines, old scheduled prompts, skipped helper calls, unavailable permissions and interrupted starts are unobserved. Duplicate calls can overcount. There is no deduplication ledger or exactly-once claim. Do not infer continuous coverage, counts before installation, or unique users/sessions.
What ships with it
3 files 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 Changed · +1 lines 58bd8614d434
- 1mo ago First seen · 131 lines · 37 tokens per session scan A d6bc07a84e39
watch-telemetry is a skill published in the GitHub repository flurdy/agent-skills (9 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,722 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-12.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…