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.
npx skills add vynazevedo/first-plan --skill reuse-indexinggit clone --depth 1 https://github.com/vynazevedo/first-planWrote 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.
[](https://agentmods.dev/skills/vynazevedo/first-plan/reuse-indexing)<a href="https://agentmods.dev/skills/vynazevedo/first-plan/reuse-indexing"><img src="https://agentmods.dev/badge/skills/vynazevedo/first-plan/reuse-indexing/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.
<a href="https://agentmods.dev/skills/vynazevedo/first-plan/reuse-indexing"><img src="https://agentmods.dev/badge/skills/vynazevedo/first-plan/reuse-indexing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00054 | $0.01252 |
| Opus 5 | $0.00027 | $0.00626 |
| Sonnet 5 | $0.00011 | $0.00250 |
| Haiku 4.5 | $0.00005 | $0.00125 |
Grade A, and why
first-plan-reuse-indexing 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reuse Indexing
Como criar .first-plan/03-reuse/ com índice invertido focado em "intenção -> existente".
Princípio
A pergunta certa nao é "o que existe?" - é "preciso fazer X, o que ja existe?". O índice é organizado por intenção, não por estrutura.
Categorias de intenção (por linguagem/stack)
Universais
| Categoria | Exemplo |
|---|---|
| Validação | "validar input HTTP" |
| Logging | "registrar evento" |
| Auth | "verificar JWT" |
| HTTP client | "chamar API externa" |
| Persistência | "buscar registro no DB" |
| Conversão / format | "formatar data" |
| Testing helper | "criar fixture" |
| Crypto | "hash de senha" |
Frontend específicas
| Categoria | Exemplo |
|---|---|
| UI components | "form com validação" |
| Hooks | "fetch com loading state" |
| State management | "store de carrinho" |
| Routing | "redirect autenticado" |
| Forms | "form com validação" |
| Modals / overlays | "dialog de confirmação" |
Critério de inclusão
Item entra no índice se:
- Usado em > 1 lugar OU claramente público (export top-level, nome inequívoco)
- API estável (nao é refator em curso, nao tem
@deprecated) - Não-trivial (re-criar custaria > 5 linhas)
- Identificável (nome semântico, não
helper.foo())
Algoritmo
Passo 1 - Coletar candidatos
Por linguagem, identifica símbolos exportados:
- Go:
func/typeem pacotepkg/ouinternal/util/ - TS:
exportem arquivoslib/,utils/,helpers/,components/,hooks/ - PHP: classes em namespaces
App\Services,App\Helpers - Python: funções/classes em módulos
utils/,helpers/,services/ - Rust:
pubemsrc/lib.rse módulos públicos
Passo 2 - Deduplica e classifica por intenção
Agrupa candidatos por categoria. Mapping comum:
| Nome contém | Categoria |
|---|---|
validate, valid, check |
Validação |
log, logger, audit |
Logging |
auth, jwt, token, permission |
Auth |
client, request, fetch, api |
HTTP client |
repository, dao, query, db |
Persistência |
format, parse, convert, to_ |
Format |
factory, builder, mock, stub |
Testing helper |
hash, encrypt, decrypt, sign |
Crypto |
Component, View, Layout |
UI components |
use<Capitalized> (TS/JS) |
React hooks |
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.
- 10d ago First seen · 146 lines · 54 tokens per session scan A 983c67586d74
first-plan-reuse-indexing is a skill published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 16d ago), licensed MIT. It adds 54 tokens to every session and 1,252 once invoked, about $0.0003 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.
Other skills, from other repositories
RecallMax
Enhances AI memory capabilities with long-context support.
agent-memory
Persistent memory system for AI coding agents. Use when you need to save facts about the user, store interaction preferences, log session events, or search previously saved memories. Triggers on remembering, saving context, recalling past decisions, or when the user says "remember this". Also use proactively when the…
snip
You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.
migrate
Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic…
lookdev
When the user says "lookdev" (or asks to tune/dial/iterate on the look of something, OR to review/edit/annotate a blog post, doc, copy, or media), stand up a local interactive studio — live controls (sliders, pickers, drag handles) for visual params, OR direct inline editing + highlight + margin comments + media…
onboarding
Onboard a project to LaunchDarkly: kickoff roadmap, resumable log, explore repo, MCP, companion flag skills, nested SDK install (detect/plan/apply), first flag. Use when adding LaunchDarkly, setting up or integrating feature flags in a project, SDK integration, or 'onboard me'.