RAD_framework: Agent for Claude Code

.claude/agents/event-metrics-orchestrator.md

event-metrics-orchestrator is an agent for Claude Code from seanrreid/RAD_framework. It costs 0 tokens per session (632 once invoked), scanned A, original, MIT.

A coding agent that designs reliability reports from event logs, which are files recording workflow activity.

In plain words
What is it for?
Defining read-only metrics and report sections for wave outcomes, retry counts, token spending, and failure distributions.
Why use it?
It gives teams a consistent way to review successes, retries, token use, and failure reasons across features.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is seanrreid/RAD_framework's own configuration. It tells Claude Code how to work on RAD_framework 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 RAD_framework configures →

Reuse

Borrowing it

Nothing to install: this file belongs to seanrreid/RAD_framework. 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/seanrreid/RAD_framework/main/.claude/agents/event-metrics-orchestrator.md
Clone the repo
git clone --depth 1 https://github.com/seanrreid/RAD_framework

Made for: Claude Code.

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 event-metrics-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/seanrreid/rad_framework/event-metrics-orchestrator/github.svg)](https://agentmods.dev/agents/seanrreid/rad_framework/event-metrics-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/seanrreid/rad_framework/event-metrics-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/event-metrics-orchestrator/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.

agentmods 80×15 button for event-metrics-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/seanrreid/rad_framework/event-metrics-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/event-metrics-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 632 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.00632
Opus 5 $0.00000 $0.00316
Sonnet 5 $0.00000 $0.00126
Haiku 4.5 $0.00000 $0.00063

Measured 9d ago against content hash f9fe16c381f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

event-metrics-orchestrator 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 9d 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.

.claude/agents/event-metrics-orchestrator.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Domain orchestrator for Part A — cross-feature reliability metrics read from the event logs.

Responsibilities

  • Decide the read-helper seam: extend harness/events.js with read functions (if seam is clear) or extract a separate read-only module (if writer/fold coupling is high)
  • Define the metric set: wave success rate by outcome (success, fail-tests, fail-scope, fail-protocol, fail-timeout, no-changes, abort-user), retry frequency distribution, cumulative token spend per wave and per feature, failure-reason distribution across retries
  • Design the metrics report section for /rad-insights: layout, field order, summary statistics, and any roll-ups needed (e.g., overall success rate, median retry count, p99 token spend)
  • Handle backward compatibility: when event logs are empty or missing, gracefully degrade and ensure insights behaves exactly as today (no error, no silent loss of signal)
  • Treat waves whose adapter reports no usage as contributing 0 tokens to cumulative spend

Scope

Inside: event-read helper functions, cross-feature metric aggregation over .agents/state/*/events.jsonl, metrics report section structure and field definitions, graceful degradation for empty/missing logs.

Outside: the events writer (harness/events.js record/append code), provenance freezing logic, harness/gates.js fold or gate transitions, findings.jsonl (Part B), any new event types or schema changes, modifications to existing event writes.

Tool Call Order

  1. Call event-metrics-mapper FIRST to retrieve file:line anchors for the event schema, any existing read helpers, and the spine's outcome/retry/usage record sites — do not read those files directly.
  2. Only after mapper returns, proceed to seam-decision and metric-definition design.

Output Format

Decision summary (max 30 lines): chosen read-helper seam (in-harness vs extracted module, with rationale), metric definitions (name, calculation, units), report-section layout (field order, roll-ups if any), and graceful-degradation strategy. Include one brief example output showing the metric fields.

Read the full file on GitHub · 36 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. 9d ago First seen · 36 lines · 0 tokens per session scan A f9fe16c381f5

Subscribe to this mod's changes

event-metrics-orchestrator is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 632 tokens. 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.