autoresearch

autoresearch is a command for Claude Code from hi0001234d/coding-agent-mcp-tools. It costs 29 tokens per session (452 once invoked), scanned A, original, Apache-2.0.

An autonomous improvement command that repeatedly changes code, checks the result against a chosen measurement, and keeps or discards each change.

In plain words
What is it for?
Use it for measurable code improvements such as debugging, security checks, documentation work, or preparing changes to ship.
Why use it?
It removes the manual cycle of making one change, running a check, judging the result, and repeating. It requires a goal, the files to change, a metric, and a verification command.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

Good fit Use it for measurable code improvements such as debugging, security checks, documentation…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/hi0001234d/coding-agent-mcp-tools/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.

Clone the repo
git clone --depth 1 https://github.com/hi0001234d/coding-agent-mcp-tools

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 autoresearch

README.md
[![agentmods](https://agentmods.dev/badge/commands/hi0001234d/coding-agent-mcp-tools/autoresearch.svg)](https://agentmods.dev/commands/hi0001234d/coding-agent-mcp-tools/autoresearch)
Your own site
<a href="https://agentmods.dev/commands/hi0001234d/coding-agent-mcp-tools/autoresearch"><img src="https://agentmods.dev/badge/commands/hi0001234d/coding-agent-mcp-tools/autoresearch.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 452 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 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 $0.00029 $0.00452
Opus 5 $0.00015 $0.00226
Sonnet 5 $0.00006 $0.00090
Haiku 4.5 $0.00003 $0.00045

Measured 7d ago against content hash 9b8a2557d5a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 7d 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

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/autoresearch.md · 32 lines

What it actually says

EXECUTE IMMEDIATELY — do not deliberate, do not ask clarifying questions before reading the protocol.

Argument Parsing (do this FIRST, before reading any files)

Extract these from $ARGUMENTS — the user may provide extensive context alongside config. Ignore prose and extract ONLY structured fields:

  • Goal: — text after "Goal:" keyword
  • Scope: or --scope <glob> — file globs after "Scope:" keyword
  • Metric: — text after "Metric:" keyword
  • Verify: — shell command after "Verify:" keyword
  • Guard: — shell command after "Guard:" keyword (optional)
  • Iterations: or --iterations — integer N for bounded mode (CRITICAL: if set, you MUST run exactly N iterations then stop)

If Iterations: N or --iterations N is found, set max_iterations = N. Track current_iteration starting at 0. After iteration N, print final summary and STOP.

Execution

  1. Read the autonomous loop protocol: .claude/skills/autoresearch/references/autonomous-loop-protocol.md
  2. Read the results logging format: .claude/skills/autoresearch/references/results-logging.md
  3. If Goal, Scope, Metric, and Verify are all extracted — proceed directly to loop setup
  4. If any critical field is missing — use AskUserQuestion with batched questions as defined in SKILL.md "Interactive Setup" section
  5. Execute the autonomous loop: Modify → Verify → Keep/Discard → Repeat
  6. If bounded: after each iteration, check current_iteration < max_iterations. If not, STOP and print summary.

IMPORTANT: Start executing immediately. Stream all output live — never run in background. Never stop early unless goal achieved or max_iterations reached.

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. 7d ago First seen · 32 lines · 29 tokens per session scan A 9b8a2557d5a8

Subscribe to this mod's changes

autoresearch is a command published in the GitHub repository hi0001234d/coding-agent-mcp-tools (11 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 452 once invoked, about $0.0001 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 2026-08-31.