tpu_performance_autoresearch_wiki: Agent for Claude Code

.claude/agents/kernel-verifier.md

kernel-verifier is an agent for Claude Code from vlasenkoalexey/tpu_performance_autoresearch_wiki. It costs 168 tokens per session (5,372 once invoked), scanned A, original, MIT.

An independent checker for experiments that optimize mathematical kernels, small programs designed for fast numerical computation. It re-runs the candidate and the simple baseline in a fresh process, checks matching results, and collects performance evidence.

In plain words
What is it for?
It is used to independently compare a candidate kernel with its baseline, verify numerical parity, inspect whether the optimization fired, and capture traces and compiler output.
Why use it?
It reduces the risk of accepting a speedup caused by noise, a measurement mistake, or an optimization that did not actually take effect. It also keeps authors from judging their own changes.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is vlasenkoalexey/tpu_performance_autoresearch_wiki's own configuration. It tells Claude Code how to work on tpu_performance_autoresearch_wiki 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 tpu_performance_autoresearch_wiki configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vlasenkoalexey/tpu_performance_autoresearch_wiki. 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/vlasenkoalexey/tpu_performance_autoresearch_wiki/main/.claude/agents/kernel-verifier.md
Clone the repo
git clone --depth 1 https://github.com/vlasenkoalexey/tpu_performance_autoresearch_wiki

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 kernel-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/vlasenkoalexey/tpu_performance_autoresearch_wiki/kernel-verifier.svg)](https://agentmods.dev/agents/vlasenkoalexey/tpu_performance_autoresearch_wiki/kernel-verifier)
Your own site
<a href="https://agentmods.dev/agents/vlasenkoalexey/tpu_performance_autoresearch_wiki/kernel-verifier"><img src="https://agentmods.dev/badge/agents/vlasenkoalexey/tpu_performance_autoresearch_wiki/kernel-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 168 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,372 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 $0.00168 $0.05372
Opus 5 $0.00084 $0.02686
Sonnet 5 $0.00034 $0.01074
Haiku 4.5 $0.00017 $0.00537

Measured 8d ago against content hash fc7d7d60ed23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

kernel-verifier 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/kernel-verifier.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the independent verifier for kernel-family experiments in the autoresearch loop. You did not author the candidate you are checking, and that is the point: per the Roles section of wiki/experiments/program.md, whoever authored a change never produces the evidence its verdict cites. You produce that evidence.

Your stance is adversarial. Actively try to show that the kernel did NOT fire, that the speedup is noise or measurement artifact, that the parity pass is a near-zero-denominator illusion, or that the author's numbers don't reproduce. A candidate that survives you has earned its verdict. If you cannot refute it, say so with your own independently measured numbers — never by repeating the author's.

The master owns experiment-page filing, verdict assignment, and next hypotheses. You ONLY verify. You do not write wiki pages, do not assign verdicts, do not propose next hypotheses, and do not modify the candidate (if it doesn't run as given, that is a finding, not something to fix).

What the master gives you

Field Example Required?
experiment_page_path /mnt/.../wiki/kernel_experiments/gemm/pallas/2026-07-12-v002-<slug>.md (ABSOLUTE) YES
index_path /mnt/.../wiki/profile-analyzer-index.md (ABSOLUTE) YES
baseline_path absolute path to the family's reference module (create_inputs + workload contract — the parity oracle; a benchmark suite's baseline.py, an in-repo reference impl, or the pinned pre-optimization target) YES
candidate_path absolute path to the final candidate (optimized.py, JAXBench-contract drop-in) YES
parity_spec atol/rtol (or "bit-exact") from the family program.md YES
chip TPU_VISIBLE_DEVICES=<n> — SHOULD differ from the chip the author benchmarked on YES
artifact_dir raw/profiles/<exp-slug>/ — where your traces + dumps land YES
python_env conda/venv activation for the benchmark process YES
author_claim the author's claimed p50 + speedup (context for reproduction check — NOT your numbers) optional
mode screen (default) or full — see Mode below optional (default screen)

If any required field is missing, refuse and ask the master for it. Do not improvise paths.

Read the full file on GitHub · 174 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. 8d ago First seen · 174 lines · 168 tokens per session scan A fc7d7d60ed23

Subscribe to this mod's changes

kernel-verifier is an agent published in the GitHub repository vlasenkoalexey/tpu_performance_autoresearch_wiki (54 stars, last pushed 4d ago), licensed MIT. It adds 168 tokens to every session and 5,372 once invoked, about $0.0008 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 2026-08-30.

Related

Other agents, from other repositories

gsd-eval-auditor

Retroactive audit of an implemented AI phase's evaluation coverage. Checks implementation against the AI-SPEC.md evaluation plan. Scores each eval dimension as COVERED/PARTIAL/MISSING. Produces a scored EVAL-REVIEW.md with findings, gaps, and remediation guidance. Spawned by /gsd-eval-review orchestrator.

mrboups/xbrain · 75 tokens

gsd-eval-planner

Designs a structured evaluation strategy for an AI phase. Identifies critical failure modes, selects eval dimensions with rubrics, recommends tooling, and specifies the reference dataset. Writes the Evaluation Strategy, Guardrails, and Production Monitoring sections of AI-SPEC.md. Spawned by /gsd-ai-integration-phase…

mrboups/xbrain · 71 tokens

gsd-integration-checker

Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end.

mrboups/xbrain · 31 tokens

gsd-nyquist-auditor

Fills Nyquist validation gaps by generating tests and verifying coverage for phase requirements.

mrboups/xbrain · 24 tokens

algorithms-researcher

Reasons from separating problem, model, and cost model (comparison, word-RAM, arithmetic, online) through exchange/matroid greedy proofs, subproblem-DAG dynamic programming, max-flow min-cut and Goemans–Williamson primal-dual rounding, Karp–Rabin fingerprinting, competitive ratio and Yao's principle, PTAS/FPTAS…

K-Dense-AI/scientific-agents · 163 tokens

astroparticle-physicist

Reasons from flux times cross section times acceptance, Poisson counting over structured backgrounds, and Cherenkov photoelectron budgets through SkyLLH unbinned likelihoods, Geant4/CORSIKA chains validated on through-going-muon and calibration samples, and Feldman-Cousins/CLs limits, while treating…

K-Dense-AI/scientific-agents · 104 tokens