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/jeongph/claude-telemetry/configgit clone --depth 1 https://github.com/jeongph/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/jeongph/claude-telemetry/config)<a href="https://agentmods.dev/commands/jeongph/claude-telemetry/config"><img src="https://agentmods.dev/badge/commands/jeongph/claude-telemetry/config.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 | $0.00014 | $0.02679 |
| Opus 5 | $0.00007 | $0.01340 |
| Sonnet 5 | $0.00003 | $0.00536 |
| Haiku 4.5 | $0.00001 | $0.00268 |
Grade B, and why
config 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 5d 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.
- If it is `auto` or missing, read `~/.claude/settings.json` `language` and map `"한국어"` → ko, `"English"` → en, `"日本語"` → ja, `"中文"` → zh. Default: en. How it starts
The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Status Line Display Configuration
You are helping the user adjust their existing status line display — preset, which
sections are shown, and how the progress bars look. This command ONLY edits
~/.claude/statusline/config.json; it does not install or remove anything.
Execution Flow
Execute steps 1 → 2 → 3 → 4 → 5 → 6 → 7 sequentially. Do NOT skip steps. Do NOT combine steps.
Step 1: Load Config & Detect Language
- Read
~/.claude/statusline/config.json. - If it does not exist, tell the user (translate to the language from settings.json, default en):
"No status line configuration found. Run
/claude-telemetry:setupfirst to install and configure the status line." Then STOP. Do NOT create a config here. - If it exists, determine the language for user-facing text:
- Use the config's
languagefield if it isko/en/ja/zh. - If it is
autoor missing, read~/.claude/settings.jsonlanguageand map"한국어"→ ko,"English"→ en,"日本語"→ ja,"中文"→ zh. Default: en.
- Use the config's
- Use this language for ALL user-facing text. Do NOT infer language from conversation context.
Step 2: Show Current State
Compute and display the current effective settings, then continue to Step 3. Keep it to a few lines (translate labels):
- Preset: value of
preset - Bar width: value of
bar_width(0= numbers only, no bar) - Enabled sections: resolve each section using the 3-layer priority —
sectionsoverride wins, otherwise the preset default (see Preset defaults table below). List the enabled ones.
Example (translate):
Current: preset=detailed, bar_width=5
Sections on: Context, Remaining, Cost, Git, PR, Elapsed, Agent, Vim, Tokens, ...
Step 3: Choose Preset
Call AskUserQuestion (translate labels/descriptions):
{
"questions": [{
"question": "<translated: Choose a preset (or keep the current one)>",
"header": "Preset",
"multiSelect": false,
"options": [
{"label": "<translated: Keep current>", "description": "<translated: Do not change the preset>"},
{"label": "<translated: Normal>", "description": "<translated: Model, Elapsed, Git, PR, Context, Remaining, Agent, Vim>"},
{"label": "<translated: Detailed>", "description": "<translated: All sections including Tokens, API Duration, Code Changes, Session>"},
{"label": "<translated: Compact>", "description": "<translated: Single line — Model, Context, Remaining>"}
]
}]
}
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.
- 5d ago First seen · 276 lines · 14 tokens per session scan B e58d32abc4aa
config is a command published in the GitHub repository jeongph/claude-telemetry (5 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 2,679 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
generate-changelog
Generate a changelog from git history, grouping commits by type and version.
test-prompt
Test an AI prompt against multiple scenarios to verify consistent, quality output.
report
Generate a project analytics report covering code quality, velocity, and health metrics.
trace
Trace the execution path of a request or operation through the codebase.
explain
Explain a code file, function, or concept in clear, structured language.
audit-deps
Audit all project dependencies for vulnerabilities, licensing issues, and maintenance status.