What is autoresearch:regression?

A regression-checking gate that compares the current code with a base Git revision, such as the main branch, using the project's own tests, benchmarks, snapshots, or migration commands.

Use it to check affected changes, performance noise, and test results in an isolated Git worktree before shipping.

It catches changes where previously passing behaviour becomes failing, and gives a stable or unstable result before pushing code.

autoresearch:regression — 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/regression/github.svg)](https://agentmods.dev/commands/wdblink/autoresearch-paper/regression)

Your own site

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

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,501 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 89% 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	$0.00034	$0.02501
Opus 5.5	$0.00014	$0.01000
Sonnet 5.5	$0.00007	$0.00500
Haiku 4.5	$0.00003	$0.00250

Measured 3d ago against content hash 1054e5b6565c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

autoresearch:regression scanned grade C with 2 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

Verify-command screen (no `rm -rf` / `curl|sh`); worktree cleanup + prune on crash; data-migration refuses any non-allowlisted DB URL; probe auto-skips non-interactively; chained `ship` never auto-deploys.

Makes network callslowCapability

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

Verify-command screen (no `rm -rf` / `curl|sh`); worktree cleanup + prune on crash; data-migration refuses any non-allowlisted DB URL; probe auto-skips non-interactively; chained `ship` never auto-deploys.

Origin

This is a copy

89% identical to autoresearch:regression — 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/regression.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EXECUTE IMMEDIATELY.

A regression is a green→red transition ONLY. The gate orchestrates the project's OWN test/bench/snapshot/migrate commands (it is a protocol, not a bundled framework), captures baseline behavior in an isolated git worktree, re-runs the candidate, and reports a tiered ship/no-ship verdict.

Parse Arguments

Extract from $ARGUMENTS:

Base: or --base — base ref to diff against. Default: git merge-base HEAD main (else main/master).
Scope: or --scope — file globs limiting the change surface.
--select auto|full|affected — test selection (default auto). auto = use the detected affected-test mapper if available, else FULL suite. Never a silent subset.
--samples N — SCORE samples/side (default 7). --noise-band % — perf tolerance (default 5%).
--matrix — opt-in matrix axis (OFF by default). --max-runs N — ceiling (default 200).
--baseline-cache (default on) — reuse baseline/<full-sha>/ by SHA. Baseline: <prebuilt-ref> — bypass capture.
--probe (default) / --probe deep / --no-probe.
--predict --reason --debug --fix --fix-cycles N --evals --evals-interval N --chain <targets> and --<sub> shorthand.
Iterations: — repeat-axis count for --select/repeat sweeps.

Setup / Probe-on-launch

Auto-detect per-dimension verify commands: package.json scripts, Makefile, nx, migrate config, bench/snapshot/size scripts.
AskUserQuestion (single batch) to confirm detected commands + base ref + which dimensions to run.
Auto-skip probe when CI / no-TTY / --mode autonomous / complete-config / chained-handoff — log the inferred config instead of asking.

Classification Phase (first-class, before any differential)

Establish the baseline green-set per dimension, then tag each unit. Match by test-id first, then path.

State	Meaning	Gated?
`regression-eligible`	green on baseline	YES — only green→red counts
`pre-existing`	red→red (already failing)	no — excluded
`new-coverage`	absent→red (brand-new test)	no — new coverage, ungated
`flaky`	nondeterministic on baseline	no — routed to flakiness SCORE
`baseline-unavailable`	dimension never green	no — advisory only

Read the full file on GitHub · 112 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 · 112 lines · 34 tokens per session scan C 1054e5b6565c

Subscribe to this mod's changes

autoresearch:regression is a command published in the GitHub repository WdBlink/autoresearch-paper (2 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 2,501 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). It is 89% identical to autoresearch:regression, differing in 0 lines, and is treated as a copy.

Git and workflow Testing academic-writing agent-skills ai ai-agents autonomous-research

autoresearch:regression next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
autoresearch:regressionWdBlink/autoresearch-paper	Command	2	4d ago	MIT	C	34	Claude Code
diff-reviewjamditis/claude-skills-journalism	Command	452	7d ago	MIT	A	16	Claude Code
list_checkpointsStill-chowline394/MagicTeX-mcp	Command	0	1mo ago	AGPL-3.0	A	14	Claude Code
merge-conflict-analysisrjmurillo/ai-agents	Command	49	today	MIT	A	0	GitHub Copilot
release-notesOpenHands/extensions	Command	181	today	MIT	A	44	Claude Code
repo-audittractorjuice/arc-kit	Command	2.3k	today	none	A	29	Claude Code
codex-reviewoalders/kitchen-sink	Command	5	3d ago	MIT	A	41	Claude Code

autoresearch:regression