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/brainOS-HQ/brain-osWrote 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/brainos-hq/brain-os/reconcile)<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="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 | $0.00000 | $0.01781 |
| Opus 5 | $0.00000 | $0.00890 |
| Sonnet 5 | $0.00000 | $0.00356 |
| Haiku 4.5 | $0.00000 | $0.00178 |
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 7d 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 — 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 intostill_true/needs_evidence/archive/changedwith a recommended action and reason for each. Whenroot_pathis provided, also runsproject_evidence_scanand matches each decision'sinvalidate_ifconditions against the scan output — matched decisions are auto-moved tochangedwithtriggered_invalidate_ifciting 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
.gitfolder 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.
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.
- 7d ago First seen · 118 lines · 0 tokens per session scan A a81bf90bbe41
reconcile is a command published in the GitHub repository brainOS-HQ/brain-os (6 stars, last pushed 13d 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.
Other commands, from other repositories
arrange-workspace-flow
Workflow for arranging a workspace: layout, reference source code, business/technical context, ecosystem setup.
ijfw-status
Show IJFW state -- mode, routing, memory, recent activity, codebase index, settings. Use when you want the at-a-glance banner you'd otherwise get at session start.
team
Manage your project's agent team. Usage: /team [setup|list|add|remove|swap].
arrange-workspace-flow-configure-ecosystem
Phase 6 Configure Ecosystem of arrange-workspace-flow.
arrange-workspace-flow-business-context
Phase 3 Business context of arrange-workspace-flow.
arrange-workspace-flow-modernization
Phase 5 Modernization of arrange-workspace-flow.