tp-performance-profiler

A performance investigation agent for finding why software behaves slowly.

In plain words
What is it for?
It is for investigating slow behaviour, response-time regressions, time to first byte, and Core Web Vitals, which are browser measures of loading and page responsiveness.
Why use it?
It measures the problem first, so fixes target the actual bottleneck instead of relying on guesses.

Agent

Part of the token-pilot plugin — 3 skills, 27 agents, 5 hooks, 1 MCP server shipped together

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 agents/digital-threads/token-pilot/tp-performance-profiler
Clone the repo
git clone --depth 1 https://github.com/Digital-Threads/token-pilot

Or install token-pilot, the plugin that ships this one along with the rest of its 3 skills, 27 agents, 5 hooks, 1 MCP server.

Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,244 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin unknown 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 $0.00070 $0.01244
Opus 5 $0.00035 $0.00622
Sonnet 5 $0.00014 $0.00249
Haiku 4.5 $0.00007 $0.00124

Measured 2d ago against content hash 9507365895f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tp-performance-profiler scanned grade A 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **Measure — establish baseline.** Ask for or run the profiling data FIRST. Backend → timing logs / tracing (`curl -w`, APM, `time`). Frontend → Lighthouse / DevTools Performance / `web-vitals` RUM. Don't accept "feels
agents/tp-performance-profiler.md · 72 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 2d ago First seen · 72 lines · 70 tokens per session scan A 9507365895f8

Subscribe to this mod's changes

tp-performance-profiler is an agent published in the GitHub repository Digital-Threads/token-pilot (5 stars, last pushed 6d ago), with no licence file. It adds 70 tokens to every session and 1,244 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.