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.
git clone --depth 1 https://github.com/felvieira/claude-skills-fvnpx agentmods add commands/felvieira/claude-skills-fv/reconcile-memoryWrote 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/commands/felvieira/claude-skills-fv/reconcile-memory)<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.
<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>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 | $0.00035 | $0.01901 |
| Opus 5 | $0.00017 | $0.00950 |
| Sonnet 5 | $0.00007 | $0.00380 |
| Haiku 4.5 | $0.00003 | $0.00190 |
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.
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-reconcilede eugeniughelbur/obsidian-second-brain (MIT). Adaptado ao nosso vault (D:\claude-memory\) e à divisão mecânico/semântico domemory-curator.
Quando usar:
- após várias sessões no mesmo projeto (decisões podem ter evoluído sem o
decisions.mdser atualizado) - antes de um
/resumeimportante (garantir que o contexto injetado não está contraditório) - quando o
memory-curatorsinalizar 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-memorysem 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 marcadasuperseded. 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: activeque 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.
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.
- 12d ago First seen · 141 lines · 35 tokens per session scan A 7644bd59e31d
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.
Other commands, from other repositories
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.