eval

A tool for measuring coding-session results, such as commits, test outcomes, duration, and other tracked indicators, then comparing them with earlier sessions.

In plain words
What is it for?
Use it to view current metrics, create or update baselines, compare recent sessions, and detect regressions.
Why use it?
It shows whether changes actually improved the work and helps spot declines over time.

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/kastalien-research/thoughtbox/eval
Any agent
npx skills add Kastalien-Research/thoughtbox --skill eval
Clone the repo
git clone --depth 1 https://github.com/Kastalien-Research/thoughtbox

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 715 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 $0.00035 $0.00715
Opus 5 $0.00017 $0.00358
Sonnet 5 $0.00007 $0.00143
Haiku 4.5 $0.00003 $0.00072

Measured 2d ago against content hash 5d85cc0bd238, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

eval 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 2d 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.

.agents/skills/eval/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluation harness: $ARGUMENTS

Commands

Parse the first word of $ARGUMENTS to determine the command:

metrics — Show current session metrics

Collect and display metrics for the current session:

  1. Count commits: git log --oneline --since="today" | wc -l
  2. Count test results: check for recent vitest output or .eval/metrics/ entries
  3. Token usage: check LangSmith state file if available
  4. Pattern usage: check .dgm/fitness.json for patterns used this session
  5. Session duration: check session start time from logs

Display as:

## Current Session Metrics

| Metric | Value | Baseline | Delta |
|--------|-------|----------|-------|
| Commits | 5 | 3.2 avg | +56% |
| Tests passing | 42/42 | 40/42 | +2 |

| Files changed | 12 | 8.5 avg | +41% |
| Patterns used | 7 | 5.3 avg | +32% |

baseline — Set or update baselines

  1. Read the last N session metric snapshots from .eval/metrics/
  2. Calculate averages for each metric
  3. Write to .eval/baselines.json
  4. Report what changed

compare — Compare sessions

Usage: compare --last N or compare --session <id>

  1. Load metric snapshots from .eval/metrics/
  2. Compare against baselines
  3. Highlight regressions (metric dropped >10% below baseline)
  4. Highlight improvements (metric improved >10% above baseline)

report — Generate weekly evaluation report

  1. Load all metrics from the past 7 days
  2. Calculate trends (improving, stable, declining)
  3. Identify top improvements and top regressions
  4. Generate recommendations based on trends

capture — Capture current session metrics

Write a metric snapshot to .eval/metrics/session-{timestamp}.json:

{
  "session_id": "<session id>",
  "timestamp": "<ISO 8601>",
  "branch": "<git branch>",
  "metrics": {
    "commits": 0,
    "tests_total": 0,
    "tests_passing": 0,
    "files_changed": 0,
    "patterns_referenced": 0,
    "assumptions_verified": 0,
    "escalations": 0,
    "spiral_detections": 0
  },
  "qualitative": {
    "session_focus": "<what the session was about>",
    "memory_usefulness": 0,
    "knowledge_gaps_found": []
  }
}

Read the full file on GitHub · 88 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. 2d ago First seen · 88 lines · 35 tokens per session scan A 5d85cc0bd238

Subscribe to this mod's changes

eval is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 715 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

reasoning

Use BEFORE answering analytical, diagnostic, planning, or multi-step reasoning questions. Trigger phrases include "should I X or Y", "why is X happening", "what's the best approach", "what are the tradeoffs", "help me think through", "diagnose", "root cause", "plan/design X", "what are the implications of", "compare…

ejentum/ejentum-mcp · 186 tokens

xcodebuildmcp-structured-output-review

Use when reviewing XcodeBuildMCP structured output schema changes, schema versioning, manifest outputSchema metadata, and JSON fixture compatibility.

getsentry/XcodeBuildMCP · 37 tokens

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…

comet-ml/opik-mcp · 147 tokens

cortex-automate

Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…

cdeust/Cortex · 93 tokens

tabnexus-mcp-evals

Generate, validate, and run isolated Codex-to-TabNexus MCP evaluations with a curated 600-query dataset, executable gold tool labels, safety checks, and best-of-three stability scoring. Use when testing TabNexus MCP tool coverage, Agent behavior, regression quality, destructive-action safety, prompt changes, or a…

KaichenCurry/TabNexus · 75 tokens

compare

Structured comparison of 2+ alternatives with consistent criteria and decision matrix.

n24q02m/wet-mcp · 15 tokens