gsd-eval-planner

An agent that designs evaluations for an AI workflow, including failure cases, scoring criteria, testing tools, and example data. It also writes evaluation, safety, and monitoring sections for an AI specification.

In plain words
What is it for?
Planning AI evaluations, defining pass and fail rubrics, choosing measurement methods, and specifying production monitoring.
Why use it?
It turns vague testing needs into measurable checks for both safe behavior and task completion.

Agent for Claude Code

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 agents/kryptobaseddev/cleo/gsd-eval-planner
Clone the repo
git clone --depth 1 https://github.com/kryptobaseddev/cleo

Made for: Claude Code.

Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,685 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 98% 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.

ModelPer sessionOnce invoked
Fable 5 $0.00071 $0.01685
Opus 5 $0.00036 $0.00843
Sonnet 5 $0.00014 $0.00337
Haiku 4.5 $0.00007 $0.00169

Measured 2d ago against content hash a57c5b3acbcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gsd-eval-planner 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.

Origin

This is a copy

98% identical to gsd-eval-planner — 4 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.

.cleo/agent-outputs/T-POMODORO-BENCH-2026-04-16/gsd/.claude/agents/gsd-eval-planner.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<required_reading> Read /tmp/pomodoro-bench/gsd/.claude/get-shit-done/references/ai-evals.md before planning. This is your evaluation framework. </required_reading>

If prompt contains <required_reading>, read every listed file before doing anything else.

<execution_flow>

Always include: safety (user-facing) and task completion (agentic).

Format each rubric as:

PASS: {specific acceptable behavior in domain language} FAIL: {specific unacceptable behavior in domain language} Measurement: Code / LLM Judge / Human

Assign measurement approach per dimension:

  • Code-based: schema validation, required field presence, performance thresholds, regex checks
  • LLM judge: tone, reasoning quality, safety violation detection — requires calibration
  • Human review: edge cases, LLM judge calibration, high-stakes sampling

Mark each dimension with priority: Critical / High / Medium.

If detected: use it as the tracing default.

If nothing detected, apply opinionated defaults:

Concern Default
Tracing / observability Arize Phoenix — open-source, self-hostable, framework-agnostic via OpenTelemetry
RAG eval metrics RAGAS — faithfulness, answer relevance, context precision/recall
Prompt regression / CI Promptfoo — CLI-first, no platform account required
LangChain/LangGraph LangSmith — overrides Phoenix if already in that ecosystem

Include Phoenix setup in AI-SPEC.md:

# pip install arize-phoenix opentelemetry-sdk
import phoenix as px
from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider

px.launch_app()  # http://localhost:6006
provider = TracerProvider()
trace.set_tracer_provider(provider)
# Instrument: LlamaIndexInstrumentor().instrument() / LangChainInstrumentor().instrument()

Read the full file on GitHub · 155 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 · 155 lines · 71 tokens per session scan A a57c5b3acbcb

Subscribe to this mod's changes

gsd-eval-planner is an agent published in the GitHub repository kryptobaseddev/cleo (160 stars, last pushed 12d ago), licensed MIT. It adds 71 tokens to every session and 1,685 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to gsd-eval-planner, differing in 4 lines, and is treated as a copy.