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.
npx skills add Eliyce/paqad-ai --skill performance-regression-estimatorgit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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.
[](https://agentmods.dev/skills/eliyce/paqad-ai/performance-regression-estimator)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/performance-regression-estimator"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/performance-regression-estimator/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.
<a href="https://agentmods.dev/skills/eliyce/paqad-ai/performance-regression-estimator"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/performance-regression-estimator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00029 | $0.00912 |
| Opus 5 | $0.00015 | $0.00456 |
| Sonnet 5 | $0.00006 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
performance-regression-estimator 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What It Does
Reads a proposed implementation outline and the changed files, scans for known performance hazards (N+1 queries, sync-in-async, missing pagination, suspicious caching, sequential network calls, hot-path logging), and classifies each by severity and hot-path placement.
The point is to catch latency and cost regressions during planning, not after a load test or a customer-facing slowdown.
Use This When
Use this in the graduated and full lanes whenever the change touches data access, request handlers, scheduled jobs, or anything with a stated latency or throughput requirement. Skip when the change is purely structural (renames, moves) and exercises no new code paths.
Inputs
- Read the proposed solution at
proposed_solution_pathfirst. - Read the changed-file list to scope hazards to code that is actually changing.
- Read canonical module docs in
module_doc_pathsfor declared latency budgets and throughput targets — a hazard on a hot path with a sub-100ms budget is much more severe than the same hazard on a daily batch job. - Read
references/perf-hazards.mdbefore classifying any hazard so the catalog and severity rubric stay consistent.
Procedure
- Enumerate code paths the change introduces/modifies (handlers, jobs, consumers, libs); mark each as hot-path or not based on canonical module docs.
- Run
scripts/scan-perf-smells.sh <changed-files...>to surface candidate hazards (N+1, await-in-loop, async-map without Promise.all, deep-clone-via-JSON, log-in-hot-path, unbounded-pagination, cache-without-invalidation, sequential-fetch). - Classify each detected hazard using
assets/severity-rubric.txt—highonly when on a hot path;mediumon cold path with unbounded volume;lowotherwise. - For every
highhazard, propose a concrete remediation tied to the samefile:line. - Format per
assets/output.template.md; validate withscripts/lint-output.sh.
Output Contract
- Return a heading named
Performance Hazards. - Provide a
Hazard Maptable with columns#,Hazard,Path,On hot path?,Severity,Remediation. - Provide a
Recommended Pre-Merge Actionsordered list of thehigh-severity hazards' remediations. - Provide an
Open Questionssection listing paths whose hot-path status could not be confirmed from the available docs. - When no hazards are detected, return
Performance Hazards: none detected.exactly.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 80 lines · 29 tokens per session scan A 44d4205d0410
performance-regression-estimator is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 912 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.
Other skills, from other repositories
pr-writing-review
Extract and analyze writing improvements from GitHub PR review comments. Use when asked to show review feedback, style changes, or editorial improvements from a GitHub pull request URL. Handles both explicit suggestions and plain text feedback. Produces structured output comparing original phrasing with reviewer…
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
auto-go
A command that implements code from a SPEC, a document describing the required behavior and work.
auto-plan
A code-planning skill that examines a codebase and creates a detailed specification, implementation plan, and acceptance criteria. It can organize requirements using EARS, a structured way to describe how software should behave in different situations.
agent-pipeline
Multi-agent pipeline orchestration skill.
adaptive-quality
Per-task execution profile selection based on complexity in Balanced quality mode.