create-skill-autoresearch

create-skill-autoresearch is a skill for Claude Code, Codex from a-tokyo/agent-skills-harness. It costs 118 tokens per session (6,166 once invoked), scanned A, a copy of create-skill-autoresearch, MIT.

A factory process for creating and testing new agent skills. It interviews the user, researches the subject, drafts the skill, improves it through repeated testing, and verifies the result with independent reviewers.

In plain words
What is it for?
Use it when building a new production-ready skill or substantially improving an existing one with research, benchmarks, automated iteration, and review.
Why use it?
It gives skill creation a defined research and evaluation process rather than producing instructions in one pass. This helps expose missing requirements and quality problems before release.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; positional $N argument; installed under .agents/ (shared by several agents).

Good fit Use it when building a new production-ready skill or substantially improving an existing one with research, benchmarks, automated iteration, and review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/a-tokyo/agent-skills-harness/create-skill-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 a-tokyo/agent-skills-harness --skill create-skill-autoresearch
Clone the repo
git clone --depth 1 https://github.com/a-tokyo/agent-skills-harness

Made for: Claude Code, Codex.

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-skill-autoresearch

README.md
[![agentmods](https://agentmods.dev/badge/skills/a-tokyo/agent-skills-harness/create-skill-autoresearch/github.svg)](https://agentmods.dev/skills/a-tokyo/agent-skills-harness/create-skill-autoresearch)
Your own site
<a href="https://agentmods.dev/skills/a-tokyo/agent-skills-harness/create-skill-autoresearch"><img src="https://agentmods.dev/badge/skills/a-tokyo/agent-skills-harness/create-skill-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 create-skill-autoresearch

Your own site · 80×15
<a href="https://agentmods.dev/skills/a-tokyo/agent-skills-harness/create-skill-autoresearch"><img src="https://agentmods.dev/badge/skills/a-tokyo/agent-skills-harness/create-skill-autoresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,166 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00118 $0.06166
Opus 5 $0.00059 $0.03083
Sonnet 5 $0.00024 $0.01233
Haiku 4.5 $0.00012 $0.00617

Measured 11d ago against content hash 61cfb028f507, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

create-skill-autoresearch scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

and the test case input as the user message. Use `curl` to an OpenAI-compatible
Origin

This is a copy

100% identical to create-skill-autoresearch — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/create-skill-autoresearch/SKILL.md · 460 lines

How it starts

The opening of the file, as written. The whole thing — 460 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Skill via Autoresearch Factory

A factory for forging production-grade agent skills through gold-standard-driven autoresearch, multi-agent verification, and structured consensus.

The factory orchestrates 4 agent roles through 5 phases:

Phase What Happens Agent Role
1. Interview Discover purpose, gold standards, scope ORCHESTRATOR
2. Research Study domain materials, build dossier, propose rubric RESEARCHER (N parallel)
3. Draft Design structure, generate SKILL.md, measure baseline BUILDER
4. Autoresearch Iterate skill against gold standards (LLM-as-judge, or an objective real-world metric for procedural skills — see 3.4) BUILDER + autoresearch skill
5. Verify Premortem, panel scoring, consensus, ship/iterate PANEL (3 subagents)

Key constraint: BUILDER and PANEL never share context. Panel receives only the skill output, gold standards, and rubric -- no bias from the building process.

Relation to create-skill

This factory extends the official single-pass skill creators (Anthropic's Skills best-practices and skill-creator; Cursor's create-skill) rather than replacing them. It adds what a one-shot generator cannot: a research dossier, gold-standard benchmarking, an autonomous improvement loop, and independent multi-agent verification. The skills it produces follow the same official conventions -- see references/skill-authoring-best-practices.md.

Companion skills

The factory orchestrates these sibling skills at runtime: autoresearch (Phase 4 improvement loop), premortem (Phase 5 risk pass), and handoff (cross-session continuity); the Phase 5 panel/consensus design draws on llm-council. In this harness they are vendored under .agents/skills/. If you install this skill standalone, install those alongside it. The factory's craft layer (references/skill-craft-principles.md) is distilled from writing-great-skills (mattpocock/skills, MIT), which the harness vendors under .agents/skills/. Phase 5 will delegate to tribunal when it is installed (see 5.2).

Read the full file on GitHub · 460 lines

Files

What ships with it

7 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.

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 · 460 lines · 118 tokens per session scan A 61cfb028f507

Subscribe to this mod's changes

create-skill-autoresearch is a skill published in the GitHub repository a-tokyo/agent-skills-harness (10 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 6,166 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to create-skill-autoresearch, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

create-notes

Write a note to {shareddir}/notes/ that future agents can actually act on. Use after every coral eval, when a heartbeat (reflect / consolidate / pivot) asks for a note, or when you discover a grader / build / runtime issue that future agents will hit. Covers 4 note variants (experiment / infra / focus / synthesis)…

Human-Agent-Society/CORAL · 217 tokens

arbor-agent-executor

Executor-dispatch phase for Arbor. Use when implementing an Idea Tree node through RunExecutor or RunExecutorParallel semantics: isolated git worktree, executor prompt construction, eval metadata injection, RunTraining policy, smoke/full evaluation, report parsing, artifact persistence, tree update, and insight…

RUC-NLPIR/Arbor · 63 tokens

arbor-agent-ideate

Strict IDEATE-stage skill for Arbor. Use immediately after TreeView(format="constraints") when drafting Idea Tree nodes, enforcing the ideadrafting and firstprinciplesprobe behavior, depth-aware idea levels, four-line TreeAddNode hypotheses, conflict checks, and self-filtering against shallow tweaks.

RUC-NLPIR/Arbor · 66 tokens

grid-ctf-ops

Operational knowledge for the gridctf scenario including strategy playbook, lessons learned, and resource references. Use when generating, evaluating, coaching, or debugging gridctf strategies.

greyhaven-ai/autocontext · 42 tokens

codex-autoresearch

Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…

leo-lilinxiao/codex-autoresearch · 80 tokens

baseline-comparison-audit

Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent…

wanshuiyin/Anti-Autoresearch · 310 tokens