docs-eval-planning

docs-eval-planning is a skill for Claude Code from supabase/evals. It costs 92 tokens per session (2,611 once invoked), scanned A, original, Apache-2.0.

A planning guide for evaluations of Supabase documentation. An evaluation is a repeatable test that checks whether a guide helps an agent produce working code.

In plain words
What is it for?
Use it to design a deterministic evaluation for a Supabase guide, including its user prompt, checks, test workspace, and scoring plan. It produces a plan, not the evaluation files.
Why use it?
It helps test the documentation itself, including cases where missing or unclear instructions cause an implementation to fail, rather than measuring the agent alone.

Skill for Claude Code ✓ vendor

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

Good fit Use it to design a deterministic evaluation for a Supabase guide, including its user prompt, checks, test workspace, and scoring plan. It produces a plan, not the evaluation files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/supabase/evals/docs-eval-planning
About the project

Supabase Evals is a test suite for measuring how well AI agents perform tasks involving Supabase, using defined scenarios, scorers, starting states, agent runtimes, and model experiments. It is for comparing agent and runtime configurations across local or hosted Supabase-like environments and recording their results. The catalogue add-ons support working with these evaluations.

supabase/evals · 136 stars · on GitHub · supabase.com

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.

Any agent
npx skills add supabase/evals --skill docs-eval-planning
Clone the repo
git clone --depth 1 https://github.com/supabase/evals

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 docs-eval-planning

README.md
[![agentmods](https://agentmods.dev/badge/skills/supabase/evals/docs-eval-planning/github.svg)](https://agentmods.dev/skills/supabase/evals/docs-eval-planning)
Your own site
<a href="https://agentmods.dev/skills/supabase/evals/docs-eval-planning"><img src="https://agentmods.dev/badge/skills/supabase/evals/docs-eval-planning/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for docs-eval-planning

Your own site · 80×15
<a href="https://agentmods.dev/skills/supabase/evals/docs-eval-planning"><img src="https://agentmods.dev/badge/skills/supabase/evals/docs-eval-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,611 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 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 5.1 $0.00092 $0.02611
Opus 5 $0.00046 $0.01306
Sonnet 5 $0.00018 $0.00522
Haiku 4.5 $0.00009 $0.00261

Measured today against content hash 89010d288dbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-18, from the pricing page.

Security

Grade A, and why

docs-eval-planning 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 today.

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.

evals/docs/.claude/skills/docs-eval-planning/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Planning a documentation eval

A documentation eval measures a page, not an agent. The prompt sends a user's request plus the page's url, and the checks say whether an agent that read the page produced working code. A gap in the page counts as a failure.

That framing is the whole difficulty. The failure modes are collected in references/flakiness.md. Read it before designing checks, not after.

What this skill produces

A plan. It does not write PROMPT.md, EVAL.ts, or a seed. Implementation and local scoring are a separate job.

The shape it takes

Model a new eval on build-docs-003-api-keys-guide or later.

build-docs-NNN-<subject>, named after the doc rather than the feature. The id is permanent. The published results series is keyed on it, so renaming breaks history. So does renaming a check.

evals/docs/build-docs-NNN-<subject>/
  PROMPT.md      frontmatter and the task the agent sees
  EVAL.ts        the scorer
  README.md      the design rationale, addressed to the next editor
  <helper>.ts    flat beside EVAL.ts, never in a subdirectory
  local/         the seed workspace

CONTRIBUTING.md makes the README.md optional. For a page under test it is required: it is the only place the stripped-word list and the constraints that must not be edited away live. Its sections:

  • What this eval measures. The page is the subject, not the agent.
  • Do not reintroduce the vocabulary. The stripped words, listed.
  • The seed carries the contract. What the seed fixes, and what each fixed thing buys and costs.
  • Do not drop the positive controls. Which checks pass for an agent that built nothing, and which ones make them mean something.
  • The guide has to actually be read.
  • What this eval does not score. Each entry with its reason. An unmeasured rule from the prompt is named here.

EVAL.ts is orchestration. Import named check* functions, assemble one flat array, return { passed: checks.every(c => c.passed), checks }, and wrap it in a try/catch whose catch returns a single self-named failure check. Split the implementations into modules and keep the full check list declared in EVAL.ts. Comment why the phase order is what it is.

Read the full file on GitHub · 206 lines

Files

What ships with it

4 files 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. today First seen · 206 lines · 92 tokens per session scan A 89010d288dbf

Subscribe to this mod's changes

docs-eval-planning is a skill published in the GitHub repository supabase/evals (136 stars, last pushed today), licensed Apache-2.0. It adds 92 tokens to every session and 2,611 once invoked, about $0.0005 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 2026-09-18.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

master-yinguang

A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.

xr843/Master-skill · 274 tokens