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.
git clone --depth 1 https://github.com/luanpdd/kit-mcpWrote 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/luanpdd/kit-mcp/reconciliar)<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/reconciliar"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/reconciliar.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.01939 |
| Opus 5 | $0.00025 | $0.00970 |
| Sonnet 5 | $0.00010 | $0.00388 |
| Haiku 4.5 | $0.00005 | $0.00194 |
Grade A, and why
reconciliar 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 4d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
O problema: o backlog foi montado num SHA passado. Desde então o HEAD avançou — findings podem ter sido resolvidas incidentalmente, executores podem ter crashado, critérios já cumpridos podem nunca ter sido marcados. Sem reconciliar, você re-executa trabalho morto ou confia em status podre.
Este comando aplica a skill reconcile-execution-backlog: para cada item, compara planned_at_sha vs HEAD, decide a ação por status e refresca o stamp.
Cria/Atualiza:
.planning/RECONCILE-REPORT.md— tabela por item (status novo, drift, ação) + contadores agregados
Após: o user tem um backlog limpo — só o que realmente sobra para executar, com SHAs frescos e findings rejeitadas removidas.
Exemplos:
/reconciliar # reconcilia todo o backlog no HEAD atual
/reconciliar --output .planning/reconcile-2026.md # output custom
Pré-requisitos:
- Repositório git com HEAD válido (
git rev-parse HEAD) - Backlog em
.planning/com itens carregando status conhecido (DONE, TODO, IN PROGRESS, BLOCKED) e, idealmente,planned_at_sha - Findings/critérios verificáveis por spot-check barato (grep/glob/test pontual)
Quando este comando é o caminho:
- O HEAD avançou muito desde que o backlog foi planejado (merge de main, hotfixes, trabalho paralelo)
- Você suspeita que findings já foram resolvidas "de graça" e não quer re-executá-las
- Um executor crashou no meio e deixou itens IN PROGRESS órfãos
- Antes de retomar execução autônoma — quer entrar com backlog confiável, não podre
1. Parsear argumentos e capturar HEAD
OUTPUT_PATH=$(echo "$ARGUMENTS" | grep -oE -- '--output [^ ]+' | awk '{print $2}')
[ -z "$OUTPUT_PATH" ] && OUTPUT_PATH=".planning/RECONCILE-REPORT.md"
HEAD_SHA=$(git rev-parse HEAD 2>/dev/null)
if [ -z "$HEAD_SHA" ]; then
echo "ERROR: HEAD inválido — não é um repositório git ou sem commits."
exit 1
fi
if [ ! -d ".planning" ]; then
echo "ERROR: .planning/ não encontrado — nada para reconciliar."
exit 1
fi
mkdir -p "$(dirname "$OUTPUT_PATH")"
echo "HEAD atual: $HEAD_SHA"
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.
- 4d ago First seen · 162 lines · 50 tokens per session scan A 6be2be69017e
reconciliar is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,939 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 2026-09-03.
Other commands, from other repositories
gsd:quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.
backlog-git
Control de versiones para backlogs de proyectos.
gsd:pause-work
Create context handoff when pausing work mid-phase.
gsd:remove-phase
Remove a future phase from roadmap and renumber subsequent phases.
weekly-summary
Generate weekly work summary from git activity.
afp
Prioritise feature - assigns ID, moves to backlog (shortcut for feature-prioritise).