instinct-promote

instinct-promote is a command for Claude Code from felvieira/claude-skills-fv. It costs 28 tokens per session (602 once invoked), scanned A, original, Apache-2.0.

A command for moving a learned project rule into the global Claude or bot configuration, so it can be used across projects.

In plain words
What is it for?
Promoting reusable conventions, such as test-file naming preferences, after they have been sufficiently validated.
Why use it?
It prevents useful, general lessons from staying isolated in one project.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/instinct.mjs promote use-fix-test-name-pattern --from=project --to=global.

Part of the dev-team-kit-fv plugin — 72 skills, 45 commands, 16 agents, 5 hooks shipped together

Good fit Promoting reusable conventions, such as test-file naming preferences, after they have been sufficiently validated.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/felvieira/claude-skills-fv
agentmods
npx agentmods add commands/felvieira/claude-skills-fv/instinct-promote

Made for: Claude Code.

Or install dev-team-kit-fv, the plugin that ships this one along with the rest of its 72 skills, 45 commands, 16 agents, 5 hooks.

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 instinct-promote

README.md
[![agentmods](https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/instinct-promote/github.svg)](https://agentmods.dev/commands/felvieira/claude-skills-fv/instinct-promote)
Your own site
<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/instinct-promote"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/instinct-promote/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 instinct-promote

Your own site · 80×15
<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/instinct-promote"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/instinct-promote.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 602 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 $0.00028 $0.00602
Opus 5 $0.00014 $0.00301
Sonnet 5 $0.00006 $0.00120
Haiku 4.5 $0.00003 $0.00060

Measured 12d ago against content hash d73c070c28fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

instinct-promote 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 12d 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.

commands/instinct-promote.md · 46 lines

What it actually says

/instinct-promote — Promover Instinct Entre Escopos

Objetivo: Promover um instinct do escopo do projeto (.bot/learned-skills/) pro escopo global (~/.claude/.bot/learned-skills/), tornando-o disponível em todos os projetos automaticamente.

Quando usar:

  • instinct atingiu score ≥ 0.8 e é genérico (não amarrado ao projeto atual)
  • padrão útil descoberto num projeto e aplicável em outros (ex: "preferência por kebab-case em test files")
  • antes de eventualmente promover pra skills/NN-name/SKILL.md formal via skill 35

Quando NÃO usar:

  • instinct específico do domínio do projeto (não generaliza)
  • score < 0.5 (ainda não validado o suficiente — ver policies/memory-tiers.md)
  • já existe instinct global com mesmo slug (use /instinct-import --overwrite se intenção for substituir)

Inputs:

  • <slug> (obrigatório) — nome do .md em .bot/learned-skills/ sem extensão
  • --from=project (default) — origem
  • --to=global (default) — destino

Output: copia o .md pro destino, anota promoted_from: + promoted_at: no frontmatter. Não deleta o original (decisão manual do user).

Comando real:

node scripts/instinct.mjs promote use-fix-test-name-pattern --from=project --to=global

Fluxo recomendado (memory-tiers.md):

.bot/learned-skills/<slug>.md  (score 0.5)
   ↓ (uso confirmado várias vezes, score sobe)
.bot/learned-skills/<slug>.md  (score ≥ 0.8)
   ↓ /instinct-promote (este comando)
~/.claude/.bot/learned-skills/<slug>.md  (global, disponível em todo projeto)
   ↓ se atingir generalidade total, skill 35 formaliza
skills/NN-<nome>/SKILL.md  (procedural, parte do kit)

Adaptado de: ECC /instinct-promote (MIT). Nosso fluxo de promoção é detalhado em policies/memory-tiers.md.

Cross-refs: /instinct-export, /instinct-import, skill 35 (skill-author), policies/memory-tiers.md.

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. 12d ago First seen · 46 lines · 28 tokens per session scan A d73c070c28fb

Subscribe to this mod's changes

instinct-promote is a command published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 28 tokens to every session and 602 once invoked, about $0.0001 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.