reality-check

reality-check is a skill for Claude Code, Codex from aretw0/agents-lab. It costs 40 tokens per session (661 once invoked), scanned A, original, MIT.

A lightweight review process for checking existing evidence and local comparisons before making a broad technical or governance decision. Prior art means related solutions or evidence that already exist.

In plain words
What is it for?
It is for deciding whether to adopt, adapt, reject, or postpone a proposed gate, policy, package-manager change, provider, worker capability, or governance rule.
Why use it?
It reduces the risk of adopting an untested idea, especially when it affects users, security, model providers, workers, publishing, or project rules.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/aretw0/agents-lab/reality-check
Any agent
npx skills add aretw0/agents-lab --skill reality-check
Clone the repo
git clone --depth 1 https://github.com/aretw0/agents-lab

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 reality-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/aretw0/agents-lab/reality-check.svg)](https://agentmods.dev/skills/aretw0/agents-lab/reality-check)
Your own site
<a href="https://agentmods.dev/skills/aretw0/agents-lab/reality-check"><img src="https://agentmods.dev/badge/skills/aretw0/agents-lab/reality-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 661 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 5.1 $0.00040 $0.00661
Opus 5 $0.00020 $0.00331
Sonnet 5 $0.00008 $0.00132
Haiku 4.5 $0.00004 $0.00066

Measured 6d ago against content hash 963777d53725, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

reality-check 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 6d 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.

packages/lab-skills/skills/reality-check/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reality-check

Use esta skill antes de transformar uma ideia em gate, primitiva, arena, política de roteamento, mudança de package manager, worker capability ou decisão de governança.

A meta é evitar desenho no vácuo sem virar burocracia. Para fatias triviais, registre apenas uma nota curta. Para decisões que afetam usuários, segurança, providers, workers ou publicação, produza um pacote explícito.

Contrato mínimo

decision:
  subject: <o que está sendo decidido>
  scope: local-safe | protected | distributed | release
  recommendation: adopt | adapt | reject | defer
evidence:
  external_or_cached_sources:
    - <url, documento local, changelog, issue, paper, benchmark ou runbook>
  local_artifacts:
    - <arquivo, teste, pacote ou workflow local comparado>
  unsupported_hypotheses:
    - <hipótese que ainda não tem evidência>
comparison:
  adopt:
    - <o que usar como está>
  adapt:
    - <o que usar com ajuste local>
  reject:
    - <o que não trazer e por quê>
checks:
  license: pass | warn | fail | not-applicable
  security: pass | warn | fail | not-applicable
  budget: pass | warn | fail | not-applicable
  governance: pass | warn | fail | not-applicable
next_step:
  smallest_safe_slice: <próxima fatia testável>
  validation: <smoke, marker-check, dry-run ou leitura bounded>

Regras

  • Preferir fontes oficiais, changelogs, issues, benchmarks, runbooks ou evidência cached já presente no repositório.
  • Não usar “o modelo sabe” como fonte.
  • Se não houver fonte externa ou cached, marcar como hipótese e reduzir a promoção.
  • Comparar com artefatos locais antes de recomendar adoção.
  • Separar adopt, adapt, reject e defer; não esconder tradeoff em texto solto.
  • Não alterar settings, roteamento, provider defaults, package manager, CI/publish ou escopo protected como efeito da checagem.
  • Não fazer chamadas remotas quando a tarefa só precisa de evidência cached/local; quando pesquisa remota for necessária, pedir autorização e citar fontes.

Read the full file on GitHub · 72 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. 6d ago First seen · 72 lines · 40 tokens per session scan A 963777d53725

Subscribe to this mod's changes

reality-check is a skill published in the GitHub repository aretw0/agents-lab (11 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 661 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

mcp-scripting

Write mcpScript JavaScript for discovering, inspecting, and calling MCP tools.

nicobailon/pi-mcp-adapter · 21 tokens

tmux-manual-qa

Run a single manual tmux-based QA scenario for the todo continuation feature against the real CLI (./pi-test.sh) in an interactive TUI. Captures scrollback, asserts deterministic pass/fail count markers, and cleans up test fixtures. Use only for the manual-qa milestone features.

code-yeongyu/senpi · 66 tokens

merge-upstream

Sync a fork branch with an upstream remote using a history-preserving merge. Use this whenever the user says /merge-upstream, merge upstream, sync upstream, sync fork, or wants upstream changes integrated without rebasing or force-pushing.

code-yeongyu/senpi · 52 tokens

gpt-image-gen

MUST read before generating images. Detailed prompt-crafting guide for gpt-image models, covering tool routing (native imagegeneration server tool vs the generateimage tool), prompt structure from subject to background, verbatim text rendering, anti-patterns, and the revisedprompt feedback loop for iteration.

code-yeongyu/senpi · 63 tokens

pi-package-sandbox-test

Use when verifying that published Pi packages install and load for normal users, including pi.dev package compatibility checks, release validation, Daytona sandbox tests, and package installability audits.

spences10/my-pi · 40 tokens

pi-primitive-check

Use when evaluating proposed Pi customisation work against built-in Pi primitives before implementation, especially extensions, packages, slash commands, and workflow ideas.

spences10/my-pi · 33 tokens