A reporting tool for reviewing how coding agents run, using Claude CLI session logs and agent-memory files to show token use, estimated API cost, run counts, duration, and success rates.

Use it to inspect all agents or one agent over today, this week, or all recorded time; view results as Markdown or JSON and optionally save a snapshot.

It helps you see which agents use the most tokens or money, run slowly, or fail often, so you can identify areas to improve.

telemetry — Skill for Claude Code and Codex by fjpulidop: A reporting tool for reviewing how coding agents run…

Install

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.

agentmods

npx agentmods add skills/fjpulidop/specrails-core/telemetry

Any agent

npx skills add fjpulidop/specrails-core --skill telemetry

Clone the repo

git clone --depth 1 https://github.com/fjpulidop/specrails-core

Made for: Claude Code, Codex.

Or install specrails, the plugin that ships this one along with the rest of its 29 skills, 14 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fjpulidop/specrails-core/telemetry.svg)](https://agentmods.dev/skills/fjpulidop/specrails-core/telemetry)

Your own site

<a href="https://agentmods.dev/skills/fjpulidop/specrails-core/telemetry"><img src="https://agentmods.dev/badge/skills/fjpulidop/specrails-core/telemetry.svg" alt="Measured on agentmods" height="20"></a>

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,219 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00055	$0.05219
Opus 5	$0.00028	$0.02610
Sonnet 5	$0.00011	$0.01044
Haiku 4.5	$0.00006	$0.00522

Measured 5d ago against content hash 967582caa681, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

telemetry 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.

find .claude/ -name "*.jsonl" \

specrails-plugin/skills/telemetry/SKILL.md · 556 lines

How it starts

The opening of the file, as written. The whole thing — 556 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze this project (read name from CLAUDE.md) agent execution telemetry — token usage, API cost estimates, run throughput, and performance trends across all sr-* agents.

Input: $ARGUMENTS — optional flags:

--period <filter> — time window for analysis. Values: today, week, all. Default: week.
--agent <name> — focus on a single agent (e.g. sr-developer). Default: all agents.
--format <fmt> — output format: markdown or json. Default: markdown.
--save — write a snapshot to .claude/telemetry/ after display.

Phase 0: Argument Parsing

Parse $ARGUMENTS to set runtime variables.

Variables to set:

PERIOD — "today", "week", or "all". Default: "week".
AGENT_FILTER — string or empty string. Default: "" (all agents).
FORMAT — "markdown" or "json". Default: "markdown".
SAVE_SNAPSHOT — boolean. Default: false.
PERIOD_START — ISO datetime lower bound derived from PERIOD and the current date/time. Set to null for "all".

Parsing rules:

Scan $ARGUMENTS for --period <value>. Valid values: today, week, all. If an unknown value is found: print Error: unknown period "<value>". Valid: today, week, all and stop. Strip from arguments.
Scan for --agent <name>. If found, set AGENT_FILTER=<name> (lowercase, strip leading sr- if the user omitted it — always normalize to sr-<name> form internally). Strip from arguments.
Scan for --format <value>. Valid: markdown, json. Unknown value: print Error: unknown format "<value>". Valid: markdown, json and stop. Strip from arguments.
Scan for --save. If found, set SAVE_SNAPSHOT=true. Strip from arguments.

Derive PERIOD_START:

today → start of today (00:00:00 UTC of the current date)
week → 7 days ago at 00:00:00 UTC
all → null (no lower bound)

Print active configuration:

Period: <today | last 7 days | all time>  Agent: <AGENT_FILTER or "all">  Format: <markdown|json>  Save: <yes|no>

Read the full file on GitHub · 556 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.

5d ago First seen · 556 lines · 55 tokens per session scan B 967582caa681

Subscribe to this mod's changes

telemetry is a skill published in the GitHub repository fjpulidop/specrails-core (9 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 5,219 once invoked, about $0.0003 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.

Analytics and metrics Code Generation ai-agents anthropic claude claude-code developer-tools

knowledge-base

Create and maintain a Markdown knowledge base that any AI agent can read, search, and update. Use when the user wants to start a knowledge base, add or update notes, organize docs/notes for an agent or LLM to consume, build an index of notes, or run a cleanup/maintenance pass on an existing MD knowledge base. Triggers…

wonderwhy-er/DesktopCommanderMCP · 112 tokens

peer-review

Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating…

xintaofei/codeg · 71 tokens

scientific-critical-thinking

Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review…

xintaofei/codeg · 63 tokens

build-teaql-app

Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…

teaql/teaql-agent-kit · 112 tokens