Skip to content
Agentmart
Submit a tool

eval-regression

Check skill routing or behavior, investigate a regression, or compare plugin changes with a base commit.

Skill by reidemeister94

IndexedMIT★ 12
Write a review

Chalk Labs

Need help deploying eval-regression?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/reidemeister94-eval-regression

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Check skill routing or behavior, investigate a regression, or compare plugin changes with a base commit.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/eval-regression

Tools it pre-approves 5

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Glob,
  • Read,
  • Bash,
  • Grep,
  • AskUserQuestion

What's inside

Skill name
eval-regression
Description
Check skill routing or behavior, investigate a regression, or compare plugin changes with a base commit.
License
MIT
Allowed tools
Glob,, Read,, Bash,, Grep,, AskUserQuestion
Instructions
29 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts
  • Pre-approves some shell commands

Files (2)

  • SKILL.md
  • run_evals.py · scripts/

SKILL.md (first lines)

# Eval regression

Use deterministic repository tests first. Stop when the target has no behavioral diff.

Resolve the plugin from the argument or cwd. Its catalog is `evals/evals.json`; the runner is `scripts/run_evals.py` in this skill.
Require the user to choose agent, model, and effort. Never select a costly model or high effort silently.

## Normal check

1. Select cases by changed paths with `--changed-from <base>`, or name them with `--case`. Do not select the full catalog implicitly.
2. Run the command without `--run`. The runner prints cases, modes, repeats, sessions, timeout, and maximum duration without starting an agent.
3. An approved plan that names this exact run already authorizes it. For a standalone eval, present the run plan and stop once.
4. After approval, repeat the same command with `--run`. Default to candidate-only, one run per case, 180 seconds, and four sessions maximum.
5. Report every failed assertion, timeout, non-zero exit, duration, and token count. Missing evidence is inconclusive.

## Escalation

- Compare base and candidate only when the user asks, or when a failed candidate check needs a baseline.
- Extract the base with `git archive`. Use the same cases, agent, model, effort, repeats, and timeout on both versions.
- Repeat only a failed or observably unstable case. Three repeats are a stability benchmark, not a default.
- `--all`, `--repeat > 1`, more sessions, or a longer timeout is new scope. Update the run plan and get authority first.
- Routing cases stop at the first Skill selection. Tool assertions are appropriate because routing is the contract.

Remove temporary base copies after the comparison. Do not edit or commit the target.

Deterministic assertions are `tool`, `tool_not`, `clean_worktree`, `changed_files_exact`, `file_contains`, `file_not_contains`, `transcript_contains`, and `tool_sequence`.
Use a semantic judge only when no filesystem, command, tool, ordering, or assistant-output observation can express the contract.

From reidemeister94/development-skills, MIT.

More from reidemeister94/development-skills

Signals

Stars
12
Forks
1
Open issues
1
Last commit (this folder)
Sep 19, 2026 (1 month ago)
Last release
Sep 20, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from reidemeister94

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get eval-regression running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying eval-regression?

CallGet help
Cite this page

eval-regression skill. Agent Mart. https://agentmart.dev/skills/reidemeister94-eval-regression (last updated 2026-10-24)