agentmods.dev

claude-telemetry: Instructions file for Claude Code

AGENTS.md

claude-telemetry AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from wangshunnn/claude-telemetry. It costs 743 tokens per session, scanned A, original, MIT.

Project instructions for a Claude Code plugin that records the agent’s hook events and shows them in an offline dashboard. The records help reveal which documentation, rules, skills, and instructions were used.

In plain words
What is it for?
Use them to work on hook wiring, event collectors, configuration, the dashboard, and the command that opens the telemetry view.
Why use it?
They make the event collection, storage, and dashboard behavior clear when changing the plugin.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

This is wangshunnn/claude-telemetry's own configuration. It tells Claude Code, Codex and OpenCode how to work on claude-telemetry itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-telemetry configures →

not rated 5repo 3mo ago A scan 743 tokens original MIT
View source ↗ wangshunnn/claude-telemetry
Reuse

Borrowing it

Nothing to install: this file belongs to wangshunnn/claude-telemetry. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/wangshunnn/claude-telemetry/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/wangshunnn/claude-telemetry

Made for: Claude Code, Codex, OpenCode.

Wrote 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.

agentmods badge for claude-telemetry AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wangshunnn/claude-telemetry/agents-md.svg)](https://agentmods.dev/instructions/wangshunnn/claude-telemetry/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/wangshunnn/claude-telemetry/agents-md"><img src="https://agentmods.dev/badge/instructions/wangshunnn/claude-telemetry/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 743 This file is loaded in full into every session.
When invoked 743 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00743 $0.00743
Opus 5 $0.00371 $0.00371
Sonnet 5 $0.00149 $0.00149
Haiku 4.5 $0.00074 $0.00074

Measured 6d ago against content hash c4313180cd3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

claude-telemetry AGENTS.md 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 6d 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.

AGENTS.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Purpose

This repository ships a Claude Code plugin that records hook events, stores them as local telemetry, and renders a self-contained offline dashboard. The core question it answers is which docs, rules, skills, and agent instructions are actually being consumed during a turn.

Project Map

  • .claude-plugin/plugin.json: Claude Code plugin manifest and user-facing metadata.
  • hooks/hooks.json: hook wiring for session, prompt (submit + slash-command expansion), tool (including Skill), notification, permission, and stop events.
  • commands/open.md: /claude-telemetry:open command definition.
  • scripts/append-event.mjs: generic event collector for most hook types, including skill_invoked from the Skill tool and slash_command from UserPromptExpansion (which is upgraded to skill_invoked when the command name resolves to an installed skill under <project>/.claude/skills/, ~/.claude/skills/, or ~/.claude/plugins/*/skills/).
  • scripts/on-stop.mjs: stop-event collector that also parses transcript usage and reply data.
  • scripts/config.mjs: default knowledge-target rules plus project-level override loading. Skill target matches any file under **/skills/<name>/** so SKILL.md, rules/, and other inner content all count as the same skill hit.
  • scripts/metrics.mjs: path normalization and knowledge-target classification helpers. Skill hits (from reads or skill_invoked events) are keyed by skill:<name> so both paths aggregate into one target.
  • scripts/build.mjs: aggregates events.jsonl into snapshot.json and a standalone HTML dashboard, applies no-data guards, and prints the generated HTML file URL (or a no-data message).
  • test/*.test.mjs: Vitest coverage for classification, config, path resolution, the build/dashboard flow, and the slash-command → skill hook path.

Working Agreements

  • Keep the plugin local-first and offline-first. Do not add network upload or remote telemetry behavior unless explicitly requested.
  • Prefer Node.js standard-library solutions and keep dependencies minimal.
  • Treat event collection as best-effort: hooks should fail soft and avoid disrupting Claude Code sessions.
  • Preserve event-shape compatibility when possible. If a schema change is necessary, make the dashboard tolerant of older rows in events.jsonl.
  • Keep generated output self-contained. The dashboard should continue to work as a single HTML file plus snapshot.json.
  • Be careful with privacy. Telemetry may contain raw prompts, absolute file paths, tool inputs, and permission commands.

Read the full file on GitHub · 40 lines

Changes

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.

  1. 6d ago First seen · 40 lines · 743 tokens per session scan A c4313180cd3a

Subscribe to this mod's changes

claude-telemetry AGENTS.md is an instructions file published in the GitHub repository wangshunnn/claude-telemetry (5 stars, last pushed 3mo ago), licensed MIT. It adds 743 tokens to every session, about $0.0037 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.

claude-codedashboardhookstelemetry
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens