autoresearch: Command for Claude Code

.opencode/commands/autoresearch_evals.md

autoresearch_evals is a command for Claude Code, OpenCode from uditgoenka/autoresearch. It costs 18 tokens per session (1,280 once invoked), scanned A, a copy of autoresearch:evals, MIT.

A results-analysis command that reads tab-separated value files, which are simple tables separated by tabs, and reports trends, flat periods, regressions, and recommendations from iterations.

In plain words
What is it for?
Use it to review iteration-result files, detect improving or worsening trends, identify plateaus, and export the analysis as text, JSON, or Markdown.
Why use it?
It helps you understand whether repeated attempts are improving a chosen measurement or have stopped making progress. It can discover result files or analyze a path you provide.

Command for Claude CodeOpenCode

Written for Claude Code and OpenCode: argument-hint in frontmatter, but also installed under .opencode/.

This is uditgoenka/autoresearch's own configuration. It tells Claude Code and OpenCode how to work on autoresearch 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 autoresearch configures →

About the project

autoresearch is an agent workflow that repeatedly changes a project, verifies a measurable result, keeps or discards the change, and continues iterating toward a goal. It is for autonomous improvement tasks in Claude Code, OpenCode, and OpenAI Codex across domains with mechanical success measures. The catalogue contains its commands, hooks, skills, plugin, agent, and instruction.

uditgoenka/autoresearch · 6,270 stars · on GitHub · udit.co

Reuse

Borrowing it

Nothing to install: this file belongs to uditgoenka/autoresearch. 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/uditgoenka/autoresearch/master/.opencode/commands/autoresearch_evals.md
Clone the repo
git clone --depth 1 https://github.com/uditgoenka/autoresearch

Made for: Claude Code, OpenCode.

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 autoresearch_evals

README.md
[![agentmods](https://agentmods.dev/badge/commands/uditgoenka/autoresearch/autoresearch_evals/github.svg)](https://agentmods.dev/commands/uditgoenka/autoresearch/autoresearch_evals)
Your own site
<a href="https://agentmods.dev/commands/uditgoenka/autoresearch/autoresearch_evals"><img src="https://agentmods.dev/badge/commands/uditgoenka/autoresearch/autoresearch_evals/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 autoresearch_evals

Your own site · 80×15
<a href="https://agentmods.dev/commands/uditgoenka/autoresearch/autoresearch_evals"><img src="https://agentmods.dev/badge/commands/uditgoenka/autoresearch/autoresearch_evals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,280 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.01280
Opus 5 $0.00009 $0.00640
Sonnet 5 $0.00004 $0.00256
Haiku 4.5 $0.00002 $0.00128

Measured 11d ago against content hash e253dab0c28d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

autoresearch_evals 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.

Origin

This is a copy

97% identical to autoresearch:evals — 6 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.

.opencode/commands/autoresearch_evals.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EXECUTE IMMEDIATELY.

Parse Arguments

Extract from $ARGUMENTS:

  • Positional path to a specific TSV file
  • --format — output format: text (default console), json, md (markdown file)
  • --compare <path> — (v2.2.0 placeholder, not yet implemented)

Input Discovery

  1. If path provided → use that TSV directly
  2. If no path → scan current directory + autoresearch/*/ for *-results.tsv files
  3. If multiple found → question: "Which results to analyze?" — list found files
  4. If none found → question: "Provide path to results TSV"
  5. Also scan project root for v2.0.03 legacy TSV files (backward compat)

Parse TSV

  1. Read line 1: extract # metric_direction: higher_is_better|lower_is_better comment
    • If missing → infer from column names (metric/error_count → guess, or ask user)
  2. Read line 2: header row → detect available columns
  3. Read remaining lines: data rows
  4. Handle missing timestamp column gracefully (v2.0.03 compat)

Column Detection & Analysis

Activate analysis based on columns present in header:

Column Analysis
metric Trend direction, plateau detection (3+ flat iterations), diminishing returns, biggest single-iteration jumps
delta Per-iteration efficiency, cumulative improvement, effort-to-gain ratio
status Keep/discard rate, crash frequency, success streaks, failure clusters, longest winning streak
guard + guard-metric Guard failure rate, metric-improved-but-guard-failed analysis
severity Severity distribution (critical/high/medium/low/info), critical discovery rate per iteration
hypothesis + status Confirmation rate, investigation efficiency, most productive techniques
commit File hotspot analysis (cross-ref with git diff for kept commits), change size correlation
technique Technique effectiveness ranking
dimension Dimension coverage completeness (X/12)
candidate_label + judge_verdict Convergence speed, oscillation count
error_type Error category distribution, fix rate per category
classification New vs extension vs duplicate ratio, saturation curve
convergence_count Convergence trajectory

Read the full file on GitHub · 119 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 · 119 lines · 18 tokens per session scan A e253dab0c28d

Subscribe to this mod's changes

autoresearch_evals is a command published in the GitHub repository uditgoenka/autoresearch (6,270 stars, last pushed 28d ago), licensed MIT. It adds 18 tokens to every session and 1,280 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to autoresearch:evals, differing in 6 lines, and is treated as a copy.