skilllint: Agent for Claude Code

.claude/agents/gsd-eval-planner.md

gsd-eval-planner is an agent for Claude Code from bitflight-devops/skilllint. It costs 72 tokens per session (1,678 once invoked), scanned A, a copy of gsd-eval-planner, MIT.

An AI evaluation planning agent that defines how an AI feature will be tested, including failure cases, scoring rules, guardrails, and production monitoring. An evaluation is a repeatable check of whether the system behaves acceptably.

In plain words
What is it for?
Use it to create evaluation plans for AI phases, choose rubrics and test data, and specify safety and task-completion monitoring.
Why use it?
It turns broad expectations into measurable checks, so teams can tell whether an AI system is safe and completes its task. It also identifies what should be measured by code, another model, or a person.

Agent for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: names the AskUserQuestion tool.

This is bitflight-devops/skilllint's own configuration. It tells Claude Code how to work on skilllint itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything skilllint configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bitflight-devops/skilllint. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bitflight-devops/skilllint/main/.claude/agents/gsd-eval-planner.md
Clone the repo
git clone --depth 1 https://github.com/bitflight-devops/skilllint

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.

agentmods badge for gsd-eval-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/bitflight-devops/skilllint/gsd-eval-planner.svg)](https://agentmods.dev/agents/bitflight-devops/skilllint/gsd-eval-planner)
Your own site
<a href="https://agentmods.dev/agents/bitflight-devops/skilllint/gsd-eval-planner"><img src="https://agentmods.dev/badge/agents/bitflight-devops/skilllint/gsd-eval-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,678 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% 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 5.1 $0.00072 $0.01678
Opus 5 $0.00036 $0.00839
Sonnet 5 $0.00014 $0.00336
Haiku 4.5 $0.00007 $0.00168

Measured 3d ago against content hash 933dacf4b2ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 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.

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

100% identical to gsd-eval-planner — 2 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/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 ./.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. 3d ago First seen · 155 lines · 72 tokens per session scan A 933dacf4b2ed

Subscribe to this mod's changes

gsd-eval-planner is an agent published in the GitHub repository bitflight-devops/skilllint (7 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 1,678 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to gsd-eval-planner, differing in 2 lines, and is treated as a copy.

Related

Other agents, from other repositories

unfolding-po

PO (Product Owner) role in the Unfolding Specs process. Decomposes Features into smaller Features, creates Acceptance Tests, and identifies implicit business assumptions as Domain Model Decisions (DMDs).

t1/tdder · 45 tokens

llm2bedrock-prompt-evaluator

Run each golden prompt against the target Bedrock model via the pinned uv harness, score with LLM-as-judge, and report a pass rate. Handles throttling with backoff; returns a structured eval object, or a partial/blocked control state.

awslabs/startups · 61 tokens

gsd-eval-planner

Designs a structured evaluation strategy for an AI phase. Identifies critical failure modes, selects eval dimensions with rubrics, recommends tooling, and specifies the reference dataset. Writes the Evaluation Strategy, Guardrails, and Production Monitoring sections of AI-SPEC.md. Spawned by /gsd:ai-integration-phase…

gsd-build/get-shit-done · 72 tokens

eval-specialist

LLM evaluation specialist. Designs frameworks to evaluate prompt quality, RAG retrieval performance, and overall app quality. Builds benchmarks, A/B tests, and regression tests.

revfactory/harness-100 · 37 tokens

llm-eval-harness-writer

Gera harness de eval LLM vs rubrica - golden dataset rotulado, LLM-as-judge (temp=0+seed), score agregado e gate CI de regressao entre versoes de prompt. Use ao medir qualidade.

luanpdd/kit-mcp · 56 tokens

fhir-data-validator

Use this agent when validating synthetic FHIR healthcare data for clinical realism and referential integrity. Triggers automatically after /generate completes or when user runs /validate command. Checks lab value ranges, medication dosages, diagnosis-appropriate patterns, date chronology, and resource references.

BACC-Labs/cynthia-generator · 59 tokens