lab:autoresearch

lab:autoresearch is a skill for Claude Code from oliver-kriska/claude-elixir-phoenix. It costs 52 tokens per session (1,193 once invoked), scanned A, original, MIT.

A repeated improvement loop for coding-agent skills. It changes one thing at a time, tests the result with a fixed scorer, and keeps or undoes the change.

In plain words
What is it for?
Improving one skill or all skills, finding their weakest areas, testing proposed changes, and recording or reverting each iteration.
Why use it?
It reduces the risk of making several changes at once and losing track of what helped or caused a regression. It also supports long unattended runs.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Improving one skill or all skills, finding their weakest areas, testing proposed changes, and recording or reverting each iteration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oliver-kriska/claude-elixir-phoenix/autoresearch
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.

Any agent
npx skills add oliver-kriska/claude-elixir-phoenix --skill autoresearch
Clone the repo
git clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenix

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 lab:autoresearch

README.md
[![agentmods](https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/autoresearch/github.svg)](https://agentmods.dev/skills/oliver-kriska/claude-elixir-phoenix/autoresearch)
Your own site
<a href="https://agentmods.dev/skills/oliver-kriska/claude-elixir-phoenix/autoresearch"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/autoresearch/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 lab:autoresearch

Your own site · 80×15
<a href="https://agentmods.dev/skills/oliver-kriska/claude-elixir-phoenix/autoresearch"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/autoresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,193 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 $0.00052 $0.01193
Opus 5 $0.00026 $0.00596
Sonnet 5 $0.00010 $0.00239
Haiku 4.5 $0.00005 $0.00119

Measured 12d ago against content hash c72c8d11ef02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

lab:autoresearch 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.

The scan reads SKILL.md. This mod also ships 8 executable files (retention.py, scripts/checks.sh, scripts/protected_sections.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

lab/autoresearch/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autoresearch — Plugin Skill Self-Improvement

Iteratively improve plugin skills via the autoresearch pattern: propose one mutation -> eval -> keep/revert -> repeat.

Usage

/lab:autoresearch                           # Targeted: attack weakest skill+dimension
/lab:autoresearch --skill review            # Focus on one skill
/lab:autoresearch --strategy sweep          # Process all skills alphabetically
/lab:autoresearch --dry-run                 # Show what would change, don't commit

For overnight runs:

/loop 5m /lab:autoresearch --strategy sweep --max-iterations 200

Iron Laws

  1. ONE mutation per iteration — if description needs "and", split into two
  2. NEVER mutate read-only files — check program.md before every write
  3. EVAL is deterministic — always use the wrapper script, never LLM-judge
  4. REVERT on regression OR checks failure — no exceptions
  5. LOG every iteration — use keep or revert command (never skip)
  6. CHECK ideas.md before proposing — don't rediscover known optimizations

Wrapper Script Commands

All eval/git/journal operations go through ONE script. Do NOT run these manually.

# Find the weakest skill+dimension
python3 lab/autoresearch/scripts/run-iteration.py target --strategy targeted

# Score a skill (before mutation, to get baseline)
python3 lab/autoresearch/scripts/run-iteration.py score <skill-name>

# After mutation: score + checks + compare → verdict (KEEP or REVERT)
python3 lab/autoresearch/scripts/run-iteration.py eval <skill-name>

# Act on verdict:
python3 lab/autoresearch/scripts/run-iteration.py keep <skill> <dim> <old> <new> \
  --desc "what changed" --asi '{"hypothesis": "why", "mechanism": "how"}'

python3 lab/autoresearch/scripts/run-iteration.py revert <skill> <dim> <old> <new> \
  --desc "what was attempted" --asi '{"hypothesis": "why", "regression": "what broke", "avoid": "do not retry this"}'

# Check overall progress
python3 lab/autoresearch/scripts/run-iteration.py status

Read the full file on GitHub · 131 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 · 131 lines · 52 tokens per session scan A c72c8d11ef02

Subscribe to this mod's changes

lab:autoresearch is a skill published in the GitHub repository oliver-kriska/claude-elixir-phoenix (544 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,193 once invoked, about $0.0003 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 skills, from other repositories

craft-pest

Testing Craft CMS 5 plugins and modules with Pest — test isolation, database safety, and the markhuot/craft-pest-core harness. ALWAYS load when writing, running, fixing, or reviewing tests for a Craft plugin or module, and whenever a suite touches a real Craft install. Covers why rollback is opt-in, tests/Pest.php +…

michtio/craftcms-claude-skills · 353 tokens

cige-test-authoring

Use when authoring, reviewing, or refactoring an agentic AI test case. Enforces the CIGE format (Context, Intent, Guardrails, Execution) that separates stable intent from adaptive, self-healing execution.

vivekkrishna/agentic-validation-skills · 51 tokens

cige-failure-classification

Use immediately after any CIGE test run completes, pass or fail, before any repair. Classifies the outcome (infrastructure failure, outdated test logic, product defect, or false positive) and names which self-healing skill, if any, is allowed to act.

vivekkrishna/agentic-validation-skills · 61 tokens

cige-product-defect-escalation

Use when cige-failure-classification identifies a Product Defect -- execution reached a healthy system with current steps, but the outcome contradicts Intent. Fetches specRef and buildRef to file a defect or, only with human approval, propose an Intent update.

vivekkrishna/agentic-validation-skills · 62 tokens

cige-stale-execution-repair

Use when cige-failure-classification identifies Outdated Test Logic (repair Execution steps, Mode A) or a confirmed False Positive (add a stricter Guardrail, Mode B). Human approval required before committing either kind of repair.

vivekkrishna/agentic-validation-skills · 56 tokens

cige-environment-recovery

Use when a CIGE test run is classified as an Infrastructure Failure (auth error, unreachable service, missing seed data, unbootstrapped environment). Restores the environment; never modifies the test definition.

vivekkrishna/agentic-validation-skills · 48 tokens