A command for reviewing old decisions that are due for a check. Each decision is considered as still true, needing evidence, changed, or ready to archive.

Use it to review decisions across a workspace or for one named project or entity. It can show simple explanations or additional structured details, and it does not archive or replace decisions automatically.

Project assumptions can become outdated, but decision records are easy to forget. This review makes it possible to revisit them with the user before changing their status.

reconcile — Command for Claude Code by brainOS-HQ/brain-os

Install

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.

Clone the repo

git clone --depth 1 https://github.com/brainOS-HQ/brain-os

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/brainos-hq/brain-os/reconcile/github.svg)](https://agentmods.dev/commands/brainos-hq/brain-os/reconcile)

Your own site

<a href="https://agentmods.dev/commands/brainos-hq/brain-os/reconcile"><img src="https://agentmods.dev/badge/commands/brainos-hq/brain-os/reconcile/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/brainos-hq/brain-os/reconcile"><img src="https://agentmods.dev/badge/commands/brainos-hq/brain-os/reconcile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,781 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01781
Opus 5.5	$0.00000	$0.00712
Sonnet 5.5	$0.00000	$0.00356
Haiku 4.5	$0.00000	$0.00178

Measured 1mo ago against content hash a81bf90bbe41, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reconcile 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 1mo 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.

templates/commands/reconcile.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brain OS : Reconcile Decision Review-Debt

Clear the decision review backlog. Walk the decisions that are due for review and, for each, decide together: still true, needs evidence, changed, or archive.

This is the user-facing loop on top of decision_review (which finds the debt) and decision_check (which flags when a premise may have changed). /decide captures a new decision; /reconcile revisits old ones.

REQUIRED FIRST READ

Before any tool call, read ~/.claude/brain-os/PROTOCOL.md. The protocol's "Tool routing" and "Mutation safety" sections are load-bearing: this command proposes, the user confirms, and nothing is archived or superseded automatically (dec-051).

Input

Arguments: $ARGUMENTS.

A project / entity name → scope the review to that entity. No name → review across the workspace.
--details (aliases: --debug, --system) → after each plain-language item, also show the System detail block (the structured reason: bucket, assumptions, invalidate_if, matched conditions). Default is plain language only.

Primary tool sequence

mcp__brain-os__decision_review(entity_id?, limit?, root_path?) : the read-only inbox. Buckets overdue decisions into still_true / needs_evidence / archive / changed with a recommended action and reason for each. When root_path is provided, also runs project_evidence_scan and matches each decision's invalidate_if conditions against the scan output — matched decisions are auto-moved to changed with triggered_invalidate_if citing the evidence. Mutates nothing.
For each item the user confirms, apply:
- mcp__brain-os__decision_refresh(decision_id, review_date?, add_evidence?, status?) : bump the review date forward, append evidence, or archive.
- mcp__brain-os__decision_log(..., supersedes=[id]) : when a decision has changed, log the replacement and supersede the old one.

Step 1: Pull the inbox

Determine whether you can supply root_path:

If you know the current working directory and it looks like a project repo (has a .git folder or known state files), use it.
If the user named a project and you know its path, use that.
If uncertain, omit root_path — the inbox still works without it, just without scan-based invalidation.

Read the full file on GitHub · 118 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.

1mo ago First seen · 118 lines · 0 tokens per session scan A a81bf90bbe41

Subscribe to this mod's changes

reconcile is a command published in the GitHub repository brainOS-HQ/brain-os (6 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,781 tokens. 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 2026-08-31.

Claude Code Planning Project management agent-memory ai-agents cursor developer-tools local-first

gsd-remove-phase

Remove a future phase from roadmap and renumber subsequent phases.

SpillwaveSolutions/agent-brain · 11 tokens

feature

Create a new feature via SDLC-based multi-agent collaboration.

sawrus/agent-guides · 11 tokens

slm-mesh

Cross-session peer coordination via the SLM mesh network. Lets multiple AI agent sessions on the same machine, and web apps the owner has allowed (ChatGPT, Claude on the web, Grok Bot, Muse, Composio), discover each other, send messages, wait for replies with meshwait, share lightweight state, and lock files to avoid…

qualixar/superlocalmemory · 150 tokens

slm-governance

Governed-workspace behavior for SuperLocalMemory. Covers roles (admin/member/viewer) and company mode, who administers a company-mode workspace (a signed-in admin, or slm team on the SLM computer), slm token show in strict mode, what remote web apps can never see or change, retention and lifecycle settings, the audit…

qualixar/superlocalmemory · 117 tokens

tree-ring-recall

Recall durable Tree Ring Memory context before starting or resuming work.

TerminallyLazy/Tree-Ring-Memory · 12 tokens

tree-ring-status

Check receipt-backed Tree Ring harness readiness without claiming configuration is activation.