tpu_performance_autoresearch_wiki: Skill for Claude Code

.claude/skills/create-retrospective/SKILL.md

create-retrospective is a skill for Claude Code from vlasenkoalexey/tpu_performance_autoresearch_wiki. It costs 253 tokens per session (10,460 once invoked), scanned A, original, MIT.

A retrospective report for one model and execution lane in an autoresearch project. It reviews all recorded experiments to show which parts of the optimization space were explored and which remain open.

In plain words
What is it for?
Use it before declaring a lane finished, after many experiments without improvement, or when repeated tests have explored only one type of change.
Why use it?
It helps distinguish a genuinely exhausted search from a stalled process that has overlooked useful directions.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

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/create-retrospective/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 create-retrospective

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/create-retrospective"><img src="https://agentmods.dev/badge/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/create-retrospective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 253 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,460 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 warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 219
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • medium Agent Snooping · line 474
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 558
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00253 $0.10460
Opus 5 $0.00127 $0.05230
Sonnet 5 $0.00051 $0.02092
Haiku 4.5 $0.00025 $0.01046

Measured 11d ago against content hash 0824f5c49cc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

create-retrospective 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 11d 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/create-retrospective/SKILL.md · 560 lines

How it starts

The opening of the file, as written. The whole thing — 560 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/create-retrospective — comprehensive lane retrospective

Maps the search space already explored on a (model, lane) pair, identifies where coverage is incomplete, and ranks unexplored directions. Run this before declaring a lane exhausted — the 2026-05-21 case (-jax declared exhausted; tokamax-CE kernel +4.18 pp landed a week later) is exactly the failure this skill exists to prevent.

When to invoke

  • The agent says "I'm out of ideas" / "all options exhausted" / "recommend pausing" — call this skill FIRST. The retrospective often surfaces a direction the agent forgot or hasn't tried.
  • The frontier hasn't moved in 10+ experiments — search strategy may need to change, not just the next probe.
  • N single-axis probes refuted on the same row with no kernel-level work tried — the imbalance pattern.
  • Manual invocation for human review/create-retrospective <model> jax produces the file; user reads + decides.
  • NOT for routine iteration — full-read of every experiment page is expensive (~250K–500K tokens for a large lane). Call this when stuck, not on every cycle.

Cardinal rules

  • Reads ALL experiments in the lane, not a sample. Coverage is the whole point.
  • Single-lane primary, cross-lane brief default ON — the brief is a 5–10 line summary of sibling lanes' frontiers + Knobs-matrix universal levers untransferred to this lane. Full cross-lane experiment-by-experiment read requires explicit --cross-lane-deep.
  • Does NOT act on its recommendations. The skill produces an analysis page; the loop / /formulate-hypothesis decides what to dispatch.
  • Does NOT update the model page or hypothesis list beyond linking to itself.
  • Does NOT auto-invoke /formulate-hypothesis — the agent reads the retrospective and decides.
  • Idempotent + dated — each invocation writes a NEW dated file; old retrospectives stay as historical record.

Arguments

Required:

  • <model> <lane> — positional. Example: /create-retrospective <model> jax.

Read the full file on GitHub · 560 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. 11d ago First seen · 560 lines · 253 tokens per session scan A 0824f5c49cc3

Subscribe to this mod's changes

create-retrospective is a skill published in the GitHub repository vlasenkoalexey/tpu_performance_autoresearch_wiki (55 stars, last pushed 7d ago), licensed MIT. It adds 253 tokens to every session and 10,460 once invoked, about $0.0013 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.