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 commands/wangshunnn/claude-telemetry/opengit clone --depth 1 https://github.com/wangshunnn/claude-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/commands/wangshunnn/claude-telemetry/open)<a href="https://agentmods.dev/commands/wangshunnn/claude-telemetry/open"><img src="https://agentmods.dev/badge/commands/wangshunnn/claude-telemetry/open.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 | $0.00018 | $0.00290 |
| Opus 5 | $0.00009 | $0.00145 |
| Sonnet 5 | $0.00004 | $0.00058 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
open scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
The command below builds the dashboard and prints either a file:// URL (on stdout) or a no-data / failure message. Do NOT run node yourself — the inline command is the single source of truth.
!node "${CLAUDE_PLUGIN_ROOT}/scripts/build.mjs"
Rules for your reply:
- Primary contract: always surface the output above to the user. If it is a
file://...URL, that URL is the answer — include it verbatim in your reply. If it is a no-data / failure message, reply with that message as-is (keep both the Chinese and English lines — do not drop either). - Opening the browser is best-effort. If (and only if) you got a
file://...URL, you MAY runopen "<url>"once to launch the browser. This call may fail withprocNotFound/ exit code 1 under Claude Code's Bash sandbox, or the user may decline the permission prompt — either way, do not retry, do not treat it as an error, and do not omit the URL from your reply. The user can click the URL themselves. - Do not invoke any other build scripts. Do not call
nodeagain.
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 · 15 lines · 18 tokens per session scan A ce74eee3d385
open is a command published in the GitHub repository wangshunnn/claude-telemetry (5 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 290 once invoked, about $0.0001 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 commands, from other repositories
rows
Configure which rows cc-statusline shows (or turn it off entirely).
autobot
Launch a bot command in an isolated autobot session with its own worktree, backend, and frontend.
fixbot
You are the orchestrator for the fixbot workflow. Fixbot fixes a Linear issue, running directly in this project against the locally running server. For an isolated worktree version, use /autobot /fixbot instead.
qabot-report
Regenerate the QA report from existing review files.
autobot-result
Print the most recent result.md for an autobot session, so the user can see how a bot is doing without attaching to its tmux session.
ci-report
Generate a CI failure report for PR $PRNUMORURL (or current branch if no argument given).