Run a budgeted Claude Code research family after plan and authority approval; routes core, debug, fix, learn, plan, predict, reason, scenario, security, and ship modes.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
## #contract.activation
```yaml
contract_schema_version: litclaude.llm-contract.v1
artifact_type: skill
skill_id: autoresearch
surface: Claude Code plugin Skill-discovery entrypoint
entry_routes: ["Skill(autoresearch)", "/litclaude:autoresearch", "$autoresearch", "leading bare autoresearch"]
verdicts: [PASS, FAIL, BLOCKED]
```
Core loop inspired by Karpathy's autoresearch. This LitClaude adapter preserves that
source-owned attribution phrase without turning source claims into measured LitClaude claims.
| Field | Contract | Evidence |
| --- | --- | --- |
| mode | One of `core`, `debug`, `fix`, `learn`, `plan`, `predict`, `reason`, `scenario`, `security`, `ship`. | Route receipt names the selected mode. |
| authority | `lit-plan` → explicit budget/authority approval → `start-work` → bounded loop → `review-work`. | Approved plan, grants, iteration receipt, and review verdict. |
| source | Read only the needed canonical files under `../../vendor/autoresearch/`. | Paths read and source commit receipt. |
## #contract.inputs
- A precise objective, measurable criterion or falsifiable question, finite iteration/time/cost budget,
…
The line at the top of this page pins the label git:20260928.d3febe7, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (8055 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
wjgoarxiv/litclaude · 3 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_57dfyg3tb3sskhsg
GET https://markdownregistry.com/api/v1/resolve?ref=wjgoarxiv/litclaude/autoresearch
GET https://markdownregistry.com/api/v1/blob/2b69c53bade3851cfb9c770bce80afe5f9e75b9629719e9ba95a4b0045eaf5b3
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
wjgoarxiv/litclaude · plugins/litclaude/skills/autoconference/SKILL.md · Run a root-owned, budgeted Claude Code research conference; routes core, analyze, debate, plan, resume, ship, and…
wjgoarxiv/litclaude · plugins/litclaude/skills/browser-drive/SKILL.md · Drive a real browser to navigate, fill, click, and extract when the answer only exists in a running page. Probes for…
wjgoarxiv/litclaude · plugins/litclaude/skills/deep-interview/SKILL.md · Socratic deep-interview loop that turns a vague idea into an execution-ready spec, using a quantitative ambiguity score…
wjgoarxiv/litclaude · plugins/litclaude/skills/lit-brainstorm/SKILL.md · Open-ended idea generation for asks like "what could we do", "give me options", "name this" or "brainstorm". Diverge…
wjgoarxiv/litclaude · plugins/litclaude/skills/lit-burnoff-file/SKILL.md · lit-burnoff-file: Removes AI-generated code smells from a SINGLE file while preserving functionality. For multiple…
wjgoarxiv/litclaude · plugins/litclaude/skills/lit-commit/SKILL.md · lit-commit: MUST USE whenever a task needs a commit or git-history investigation. Covers atomic commits, staging…
github/awesome-copilot · skills/autoresearch/SKILL.md · Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable…
orchestra-research/ai-research-skills · 0-autoresearch-skill/SKILL.md · Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid…
ericosiu/ai-marketing-skills · autoresearch/SKILL.md · Run Karpathy-style autoresearch optimization on any content. Generates 50+ variants, scores with a 5-expert simulated…
yeachan-heo/gajae-code · packages/coding-agent/src/defaults/gjc/skills/autoresearch/SKILL.md · Goal-directed research missions that interleave web research with data experimentation and end on a structured…
