evaluate-run

evaluate-run is a skill for Claude Code, Codex from adrianco/retort. It costs 45 tokens per session (4,380 once invoked), scanned A, original, Apache-2.0.

A tool for checking one Retort experiment run against the task requirements. Retort is a system that tests coding agents across planned combinations of models, languages, and tools.

In plain words
What is it for?
Use it to inspect a run's TASK.md requirements, execute its build and tests, calculate results, and save both a readable report and structured findings.
Why use it?
It turns a generated code workspace into a repeatable report, so you can see whether the requested work was implemented and whether it builds and passes tests.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/adrianco/retort/evaluate-run
Any agent
npx skills add adrianco/retort --skill evaluate-run
Clone the repo
git clone --depth 1 https://github.com/adrianco/retort

Made for: Claude Code, Codex.

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 evaluate-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/adrianco/retort/evaluate-run.svg)](https://agentmods.dev/skills/adrianco/retort/evaluate-run)
Your own site
<a href="https://agentmods.dev/skills/adrianco/retort/evaluate-run"><img src="https://agentmods.dev/badge/skills/adrianco/retort/evaluate-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,380 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00045 $0.04380
Opus 5 $0.00023 $0.02190
Sonnet 5 $0.00009 $0.00876
Haiku 4.5 $0.00005 $0.00438

Measured 3d ago against content hash 5ad1ce901284, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluate-run 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.

The scan reads SKILL.md. This mod also ships 1 executable file (evaluate-run.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/evaluate-run/SKILL.md · 347 lines

How it starts

The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluate Retort Run

Overview

A retort run produces a workspace directory — generated source code for one factor-level combination — archived under <experiment>/runs/<cell>/rep<N>/. This skill evaluates that workspace against the task spec it was asked to implement, captures quantitative and qualitative findings, and writes results in a format comparable across runs.

This is the per-run counterpart to pourpoise's evaluate-attempt, adapted for retort's DoE structure: instead of ad-hoc attempts, each run is a point in a design matrix.

Parameters

  • run_dir (required): Path to the archived run workspace, e.g. experiment-1/runs/language=rust_model=opus_tooling=beads/rep2/
  • output_file (optional, default: {run_dir}/evaluation.md): Where to write the human-readable report
  • findings_file (optional, default: {run_dir}/findings.jsonl): Where to write structured findings (one JSON object per line) suitable for file-run-issues

Inputs You Can Rely On

Each run_dir is laid out by retort's LocalRunner and contains:

File Purpose
TASK.md Task spec — the prompt the agent received. This is the "requirements" source of truth.
stack.json {"language": ..., "agent": ..., "framework": ...} — the factor levels for this run
All generated source files Exactly as the agent left them
Possibly .beads/ Only if tooling=beads was in effect — the agent used bd for tracking
Possibly build artifacts node_modules/, target/, __pycache__/, etc.

The retort database (experiment-<N>/retort.db) also holds this run's ExperimentRun + RunResult rows. You MAY query it read-only for cross-checking scores; you MUST NOT write to it.

Steps

1. Verify the run workspace

test -d "{run_dir}" || { echo "run_dir missing"; exit 1; }
test -f "{run_dir}/TASK.md" || { echo "TASK.md missing — not a retort workspace"; exit 1; }
test -f "{run_dir}/stack.json" || { echo "stack.json missing"; exit 1; }

Read the full file on GitHub · 347 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 347 lines · 45 tokens per session scan A 5ad1ce901284

Subscribe to this mod's changes

evaluate-run is a skill published in the GitHub repository adrianco/retort (199 stars, last pushed 4d ago), licensed Apache-2.0. It adds 45 tokens to every session and 4,380 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens