perf

perf is a command for coding agents from aneja5/forge-skills. It costs 19 tokens per session (178 once invoked), scanned A, original, MIT.

A command for defining limits on response time, AI-call cost, caching, and frontend bundle size. These limits describe how much latency, money, and downloaded code the system should use.

In plain words
What is it for?
Use it to set request and AI-call budgets, choose cache behavior, limit initial JavaScript size, and identify the busiest or slowest areas to profile.
Why use it?
It makes performance and spending expectations explicit and gives the team targets to check instead of optimizing without clear limits.

Command

Part of the forge-skills plugin — 42 skills, 36 commands, 13 agents, 1 hook 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 commands/aneja5/forge-skills/perf
Clone the repo
git clone --depth 1 https://github.com/aneja5/forge-skills

Or install forge-skills, the plugin that ships this one along with the rest of its 42 skills, 36 commands, 13 agents, 1 hook.

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 perf

README.md
[![agentmods](https://agentmods.dev/badge/commands/aneja5/forge-skills/perf.svg)](https://agentmods.dev/commands/aneja5/forge-skills/perf)
Your own site
<a href="https://agentmods.dev/commands/aneja5/forge-skills/perf"><img src="https://agentmods.dev/badge/commands/aneja5/forge-skills/perf.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 178 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 $0.00019 $0.00178
Opus 5 $0.00010 $0.00089
Sonnet 5 $0.00004 $0.00036
Haiku 4.5 $0.00002 $0.00018

Measured 4d ago against content hash 2f902d55aff1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

commands/perf.md · 14 lines

What it actually says

Invoke the forge-skills:performance-and-cost-optimization skill.

Define latency budgets per request type — interactive <200ms, API read <500ms p95, background <30s. For every LLM call: model selection rationale, input token cap, max_tokens, cost-per-call target, per-user-per-day budget. Design caching strategy — key schema with version, TTLs, invalidation events table, negative caching, failure mode. Set frontend bundle budget (<200KB initial JS per route), enforce via CI. Identify profiling targets — top 3 by traffic, top 3 by latency, top 3 DB queries. Profile before optimizing.

After writing: "Performance budget written to .forge/performance-budget.md. Pair with /observe to track compliance."

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. 4d ago First seen · 14 lines · 19 tokens per session scan A 2f902d55aff1

Subscribe to this mod's changes

perf is a command published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 19 tokens to every session and 178 once invoked, about $0.0001 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.