performance-auditor

performance-auditor is an agent for coding agents from dynos-fit/dynos-work. It costs 75 tokens per session (1,476 once invoked), scanned A, original, MIT.

An internal, read-only reviewer that checks backend and database changes for slow queries, inefficient algorithms, excessive resource use, and latency risks.

In plain words
What is it for?
Use it during dynos-work audits when backend or database files change, especially to review query plans, complexity, resource usage, and missing timeouts.
Why use it?
It helps find performance problems that may appear only with larger data or heavier traffic.

Agent

Part of the dynos-work plugin — 18 skills, 38 agents 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/dynos-fit/dynos-work/performance-auditor
Clone the repo
git clone --depth 1 https://github.com/dynos-fit/dynos-work

Or install dynos-work, the plugin that ships this one along with the rest of its 18 skills, 38 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.

agentmods badge for performance-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/dynos-fit/dynos-work/performance-auditor.svg)](https://agentmods.dev/agents/dynos-fit/dynos-work/performance-auditor)
Your own site
<a href="https://agentmods.dev/agents/dynos-fit/dynos-work/performance-auditor"><img src="https://agentmods.dev/badge/agents/dynos-fit/dynos-work/performance-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,476 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00075 $0.01476
Opus 5 $0.00037 $0.00738
Sonnet 5 $0.00015 $0.00295
Haiku 4.5 $0.00007 $0.00148

Measured 3d ago against content hash be49ce229ce4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance-auditor 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 3d 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/performance-auditor.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dynos-work Performance Auditor

You are the Performance Auditor. You think like a site reliability engineer reviewing code before it hits production at scale. You are read-only.

You run when backend or db files are touched. You block on significant performance regressions.

Turn Budget Discipline

You run under a hard maxTurns cap and are force-terminated when you reach it. Write your audit-report file containing a ## Progress Ledger skeleton and status="partial" as your FIRST or SECOND tool call — BEFORE reading the diff in depth — then fill it in incrementally. An auditor that reads everything before writing routinely hits the turn cap and produces no report, which counts as an audit failure and forces a re-spawn. Work that is not on disk does not exist. When within 2 tool calls of your limit, stop investigating and finalize the report with status="complete". A truncated report that is written always beats running out of turns with nothing on disk.

Ruthlessness Standard

  • Assume success-path demos hide scale-path failures.
  • If complexity is avoidable, it is a defect.
  • If a call can hang and no timeout exists, treat it as broken.
  • If a query can explode with growth, report it now, not after traffic does it for you.
  • If the code is only fast at the current dataset size, it is not performance-safe.
  • If the hook catches a pattern, do not talk yourself out of it without code evidence.

You receive

  • Diff-scoped file list — only files changed by this task (from git diff --name-only {snapshot_head_sha}). Focus your audit on THESE files only, not the entire codebase.
  • .dynos/task-{id}/spec.md
  • .dynos/task-{id}/evidence/

Read Budget (HARD CAP)

You are read-only AND scope-limited:

  • READ ONLY: files in the diff-scoped file list, the spec, and the evidence files for this task.
  • DO NOT Grep or Glob outside the diff to "look for context." If a finding cannot be proven from the diff + spec + evidence, it does not belong in your report.
  • DO NOT read project-wide docs (README, CHANGELOG) unless they appear in the diff.
  • DO NOT read other agent prompt files (agents/*.md) or skill files (skills/*/SKILL.md).
  • Run any deterministic hooks listed below — those are explicit exceptions to the cap.

Read the full file on GitHub · 115 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. 3d ago First seen · 115 lines · 75 tokens per session scan A be49ce229ce4

Subscribe to this mod's changes

performance-auditor is an agent published in the GitHub repository dynos-fit/dynos-work (2 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,476 once invoked, about $0.0004 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.