reconcile-memory

reconcile-memory is a command for Claude Code from felvieira/claude-skills-fv. It costs 35 tokens per session (1,901 once invoked), scanned A, original, Apache-2.0.

A workflow for finding and resolving contradictions in a project’s memory vault, such as decisions that changed but were never updated. A memory vault is a collection of notes used to preserve project context between sessions.

In plain words
What is it for?
Use it after many sessions, before an important resume or major release, or when the memory curator flags possible conflicts. It is unnecessary for a new vault with very few stored decisions or immediately after the same check.
Why use it?
It prevents the stored project context from containing conflicting instructions or outdated decisions. This reduces the chance that future work starts from an incorrect understanding.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents; names the AskUserQuestion tool.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/curator-state.mjs --write --vault "$VAULT".

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

Good fit Use it after many sessions, before an important resume or major release, or when the memory curator flags possible conflicts. It is unnecessary for a new vault with very few stored decisions or immediately after the same check.

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/reconcile-memory

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 reconcile-memory

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/reconcile-memory"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/reconcile-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,901 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 $0.00035 $0.01901
Opus 5 $0.00017 $0.00950
Sonnet 5 $0.00007 $0.00380
Haiku 4.5 $0.00003 $0.00190

Measured 12d ago against content hash 7644bd59e31d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

reconcile-memory 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/reconcile-memory.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/reconcile-memory — Resolução de Contradições no Vault

Objetivo: o vault nunca deve conter duas notas que se contradizem sem saber que se contradizem. Cada contradição é resolvida ou documentada como questão aberta. Complementa /consolidate-memory (que faz dedup/archive) com uma capacidade nova: detecção semântica de conflitos.

Inspiração: /obsidian-reconcile de eugeniughelbur/obsidian-second-brain (MIT). Adaptado ao nosso vault (D:\claude-memory\) e à divisão mecânico/semântico do memory-curator.

Quando usar:

  • após várias sessões no mesmo projeto (decisões podem ter evoluído sem o decisions.md ser atualizado)
  • antes de um /resume importante (garantir que o contexto injetado não está contraditório)
  • quando o memory-curator sinalizar candidatos em .curator-pending.md
  • antes de release major (limpar decisões superadas)

Quando NÃO usar:

  • vault recém-criado (< 10 decisões/logs — nada pra contradizer)
  • logo após um /reconcile-memory sem novas sessões

Skill ativada: Context Manager (skill 08) em modo "vault truth-keeper".

Pré-requisito inviolável

Antes de QUALQUER leitura, aplicar policies/memory-write-rules.md:

  • False absence: nunca conclua "não há contradição" sem varredura exaustiva. Enumere, não amostre.
  • No fabrication: nunca invente uma contradição que não existe pra parecer produtivo. Zero contradições é um resultado válido.

Processo

Passo 1 — Snapshot (igual ao consolidate)

VAULT="${1:-D:/claude-memory}"
TS=$(date +%Y-%m-%d-%H%M)
if [ -d "$VAULT/.git" ]; then
  cd "$VAULT" && git add -A && git commit -m "snapshot pre-reconcile $TS"
else
  cp -r "$VAULT" "$VAULT.bak.$TS"
fi

Passo 2 — Varredura de contradições (4 eixos)

Argumento opcional $ARGUMENTS = tópico/projeto pra focar. Sem ele, varre o vault todo. Para escala, despachar subagents em paralelo (um por eixo):

  • Decisões revertidas (architecture/<projeto>/decisions.md): pares de decisões sobre o mesmo tópico onde a mais nova reverte a antiga, mas a antiga nunca foi marcada superseded. Ex: "decidimos usar REST" depois "migramos pra GraphQL" sem atualizar a primeira.
  • Fatos stale entre logs: claims factuais em logs diferentes que se contradizem (versão de lib, status de feature, nome de arquivo). O mais recente geralmente vence.
  • Decisões superadas sem ref: decisões status: active que um log posterior descreve como abandonada/mudada.
  • Recency drift: claim externo sem (as of ...) que um log mais novo atualiza com data — flag pra adicionar o marker.

Read the full file on GitHub · 141 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. 12d ago First seen · 141 lines · 35 tokens per session scan A 7644bd59e31d

Subscribe to this mod's changes

reconcile-memory is a command published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 1,901 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.