tpu_performance_autoresearch_wiki: Skill for Claude Code

.claude/skills/formulate-hypothesis/SKILL.md

formulate-hypothesis is a skill for Claude Code from vlasenkoalexey/tpu_performance_autoresearch_wiki. It costs 0 tokens per session (8,729 once invoked), scanned A, original, MIT.

A structured hypothesis generator for an autoresearch optimization loop, which repeatedly tests model changes. It combines general optimization guidance with the selected model, execution lane, variant, and search mode.

In plain words
What is it for?
Use it to prepare a frontier, exploratory, or bootstrap experiment hypothesis, including the expected result and conditions that would disprove it.
Why use it?
It makes proposed experiments explicit and reviewable instead of relying on undocumented guesses about what change to try next.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; positional $N argument.

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/skills/formulate-hypothesis/SKILL.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 formulate-hypothesis

README.md
[![agentmods](https://agentmods.dev/badge/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/formulate-hypothesis/github.svg)](https://agentmods.dev/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/formulate-hypothesis)
Your own site
<a href="https://agentmods.dev/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/formulate-hypothesis"><img src="https://agentmods.dev/badge/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/formulate-hypothesis/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 formulate-hypothesis

Your own site · 80×15
<a href="https://agentmods.dev/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/formulate-hypothesis"><img src="https://agentmods.dev/badge/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/formulate-hypothesis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,729 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00000 $0.08729
Opus 5 $0.00000 $0.04365
Sonnet 5 $0.00000 $0.01746
Haiku 4.5 $0.00000 $0.00873

Measured 12d ago against content hash 7c2b26841047, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

formulate-hypothesis 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.

.claude/skills/formulate-hypothesis/SKILL.md · 502 lines

How it starts

The opening of the file, as written. The whole thing — 502 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are formulating one optimization hypothesis for the autoresearch loop. The output of this skill MUST be a structured proposal that the master agent reviews before dispatching. Do not skip steps.

Step 1 — Gather inputs from caller / session context

The caller (typically the loop in /start-experiment Step 9, step 2(c)(i)) provides:

  • <model> + <lane> — e.g. <model> + jax
  • <variant> — current variant being optimized (e.g. 3B/v5p-16, 24B/v5p-32)
  • <mode> (optional, default frontier) — one of:
    • frontier (default): variant has a measured-best baseline and regression would be costly. Full ceremony. Pick this when the model page's variant matrix shows a non-trivial Current best for the variant.
    • exploration: variant is early-stage, stuck, or being probed. Lighter ceremony, hunches allowed. Pick for stalled variants where the ladder has saturated, or when probing a hypothesis category the wiki doesn't yet cover.
    • bootstrap: brand-new model with thin/no per-model state (no per-model refuted-patterns.md, no retrospectives, variant matrix has < 3 rows or no Current best). Even lighter ceremony — Steps 4, 5 degrade gracefully; first-principles reasoning from index + blueprint is the primary input. See the "Bootstrap mode" section below for the auto-detection rule and the full mode-specific override behavior.
    • user-override: the caller has specified an exact candidate (passed in <user_specified_candidate>). Skill skips hypothesis generation and just validates the candidate (refuted-pattern check + topic fit + semantics-preservation check), then emits the proposal.
  • <user_specified_candidate> (optional, REQUIRED if <mode> is user-override) — the exact hypothesis the caller wants validated (one sentence, falsifiable form).
  • <topic_hint> (optional) — caller's best guess at the topic. If not provided, infer from recent profile / frontier-shift conversation.
  • <recent_profile_summary> (optional but strongly preferred) — bucket attribution from the most recent xprof. If absent, the proposal should recommend capturing a profile first rather than committing to a candidate.
  • <current_frontier> — MFU + experiment ID of the variant's current frontier
  • <last_2_3_experiments> — what was just tried, with verdicts
  • <in_flight_v_ids> — workload v-IDs other tracks are running, so the proposal steers clear of duplicates

If any input is missing AND not derivable from session context, ask the caller for it before proceeding. Do not invent.

Read the full file on GitHub · 502 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. 12d ago First seen · 502 lines · 0 tokens per session scan A 7c2b26841047

Subscribe to this mod's changes

formulate-hypothesis is a skill published in the GitHub repository vlasenkoalexey/tpu_performance_autoresearch_wiki (55 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 8,729 tokens. 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.