cognia-agents: Agent for Claude Code

.claude/agents/cognia-perf.md

cognia-perf is an agent for Claude Code from atmosware/cognia-agents. It costs 67 tokens per session (127 once invoked), scanned A, original, MIT.

A performance audit agent for an existing software project. It identifies the project type and checks possible slowdowns in database queries, rendering, network requests, memory use, startup, and concurrent work.

In plain words
What is it for?
Use it to investigate performance in backend, frontend, iOS, Android, or mixed projects and to identify likely bottlenecks.
Why use it?
It helps locate the parts of an application that may be making it slow or resource-heavy. Recommendations are prioritised to help focus improvement work.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is atmosware/cognia-agents's own configuration. It tells Claude Code how to work on cognia-agents 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 cognia-agents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to atmosware/cognia-agents. 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/atmosware/cognia-agents/main/.claude/agents/cognia-perf.md
Clone the repo
git clone --depth 1 https://github.com/atmosware/cognia-agents

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 cognia-perf

README.md
[![agentmods](https://agentmods.dev/badge/agents/atmosware/cognia-agents/cognia-perf/github.svg)](https://agentmods.dev/agents/atmosware/cognia-agents/cognia-perf)
Your own site
<a href="https://agentmods.dev/agents/atmosware/cognia-agents/cognia-perf"><img src="https://agentmods.dev/badge/agents/atmosware/cognia-agents/cognia-perf/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 cognia-perf

Your own site · 80×15
<a href="https://agentmods.dev/agents/atmosware/cognia-agents/cognia-perf"><img src="https://agentmods.dev/badge/agents/atmosware/cognia-agents/cognia-perf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 127 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 $0.00067 $0.00127
Opus 5 $0.00034 $0.00063
Sonnet 5 $0.00013 $0.00025
Haiku 4.5 $0.00007 $0.00013

Measured 8d ago against content hash 5ea6188f8aa8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cognia-perf 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 8d 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/cognia-perf.md · 7 lines

What it actually says

Canonical definition: Read .github/agents/cognia-perf.agent.md and follow every instruction defined there exactly. This file exists only to register the agent — all role, responsibilities, constraints, approach, and output format are in the canonical file.

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. 8d ago First seen · 7 lines · 67 tokens per session scan A 5ea6188f8aa8

Subscribe to this mod's changes

cognia-perf is an agent published in the GitHub repository atmosware/cognia-agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 127 once invoked, about $0.0003 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.