What is autoresearch:predict?

A pre-implementation review in which several expert viewpoints debate a proposed change and check the result against a goal.

Use it to analyse selected files, run multiple debate rounds, apply adversarial reviewers, limit findings, or fail a continuous-integration check at a chosen severity.

It surfaces concerns about code quality, security, performance, or architecture before implementation begins.

autoresearch:predict — Command for Claude Code by WdBlink

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.

Clone the repo

git clone --depth 1 https://github.com/WdBlink/autoresearch-paper

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/wdblink/autoresearch-paper/predict/github.svg)](https://agentmods.dev/commands/wdblink/autoresearch-paper/predict)

Your own site

<a href="https://agentmods.dev/commands/wdblink/autoresearch-paper/predict"><img src="https://agentmods.dev/badge/commands/wdblink/autoresearch-paper/predict/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/wdblink/autoresearch-paper/predict"><img src="https://agentmods.dev/badge/commands/wdblink/autoresearch-paper/predict.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 952 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.

Origin 97% 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.

Model	Per session	Once invoked
Fable 5.1	$0.00013	$0.00952
Opus 5.5	$0.00005	$0.00381
Sonnet 5.5	$0.00003	$0.00190
Haiku 4.5	$0.00001	$0.00095

Measured 3d ago against content hash b801ead0e607, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

autoresearch:predict 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 3d 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.

Origin

This is a copy

97% identical to autoresearch:predict — 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.

.claude/commands/autoresearch/predict.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EXECUTE IMMEDIATELY.

Parse Arguments

Extract from $ARGUMENTS:

Scope: or --scope — file globs to analyze
Goal: or --goal — focus area for analysis
Depth: or --depth — shallow (3 personas, 1 round), standard (5, 2), deep (8, 3)
--personas N — override persona count (3-8)
--rounds N — override debate rounds (1-3)
--adversarial — use hostile reviewer personas instead of default
--budget N — max findings across all personas (default 40)
--fail-on <severity> — CI gate: exit non-zero if findings at/above threshold
--incremental — reuse existing knowledge files, update only changed files
--chain, --<subcommand>

Remaining text not matching flags = goal description.

Setup (if Scope or Goal missing)

AskUserQuestion (single batch): Q1 (Scope): "Which files to analyze?" — suggested globs + entire codebase Q2 (Goal): "What should personas focus on?" — code quality, security, performance, architecture, all Q3 (Depth): "How deep?" — shallow (3 personas, 1 round), standard (5, 2 — recommended), deep (8, 3) Q4 (Chain): "After analysis, chain to?" — debug, security, fix, ship, scenario, no chain If all provided → skip.

Phase 1: Reconnaissance

Scan all in-scope files. Build structured knowledge:

File inventory with purpose annotations
Dependency graph (imports/exports)
API surface (routes, handlers, types)
Data flow (inputs → processing → outputs → storage)
Existing test coverage map

Phase 2: Persona Generation

Load references/predict-personas.md for persona definitions.

Default set (5): Architect, Security Analyst, Performance Engineer, Reliability Engineer, Devil's Advocate. Adversarial set (--adversarial): Breaker, Cheater, Scaler, Newbie, Malicious Insider.

Each persona receives: task description + codebase knowledge + their specific evaluation criteria. Personas are isolated — no shared context between them.

Phase 3: Independent Analysis

Each persona analyzes the codebase independently:

Read relevant code through their lens
Produce findings with: title, severity, confidence (0-100%), file:line, recommendation
Max findings per persona: budget / persona_count

Read the full file on GitHub · 96 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.

3d ago First seen · 96 lines · 13 tokens per session scan A b801ead0e607

Subscribe to this mod's changes

autoresearch:predict is a command published in the GitHub repository WdBlink/autoresearch-paper (2 stars, last pushed 4d ago), licensed MIT. It adds 13 tokens to every session and 952 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to autoresearch:predict, differing in 0 lines, and is treated as a copy.

Code review academic-writing agent-skills ai ai-agents autonomous-research

autoresearch:predict next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
autoresearch:predictWdBlink/autoresearch-paper	Command	2	4d ago	MIT	A	13	Claude Code
diff-reviewjamditis/claude-skills-journalism	Command	452	7d ago	MIT	A	16	Claude Code
plan-reviewjamditis/claude-skills-journalism	Command	452	7d ago	MIT	A	16	Claude Code
fact-checkjamditis/claude-skills-journalism	Command	452	7d ago	MIT	A	17	Claude Code
concurrency-code-reviewoghie/skillsets	Command	9	1mo ago	MIT	A	0	Claude Code
ultra-agentsStill-chowline394/MagicTeX-mcp	Command	0	1mo ago	AGPL-3.0	A	0	Claude Code
resolve_commentStill-chowline394/MagicTeX-mcp	Command	0	1mo ago	AGPL-3.0	A	0	Claude Code