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.
npx agentmods add commands/brainos-hq/brain-os/queuegit clone --depth 1 https://github.com/brainOS-HQ/brain-osWhat 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 | $0.00000 | $0.00700 |
| Opus 5 | $0.00000 | $0.00350 |
| Sonnet 5 | $0.00000 | $0.00140 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
queue 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 2d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brain OS : What's in Queue
"What's coming up — plan steps, releases, backlog, and overdue decisions?"
Not a focus engine. A pipeline view. Shows the ordered queue of what's next, not just what's now.
REQUIRED FIRST READ
Before any tool call, read ~/.claude/brain-os/PROTOCOL.md.
Input
Arguments: $ARGUMENTS (optional project name to scope to one entity, e.g. "brain os" or "my-app")
Primary tool sequence
mcp__brain-os__context_resolve(user_message=$ARGUMENTS)— resolve scope if a project is namedmcp__brain-os__plan_read(entity_id)— get the active plan and pending stepsmcp__brain-os__entity_read(entity_id)— get open questions and backlog signalsmcp__brain-os__decision_review(entity_id, limit=5)— surface overdue decision reviews
If no project is named, call entity_read() for all entities, then show the global queue view.
Output format
BRAIN OS — QUEUE
═══════════════════════════════════════
ACTIVE NOW
→ [current plan step]
BLOCKERS (act first)
🔴 [project]: [what is blocked and why]
OVERDUE DECISIONS (review before proceeding)
- "[decision]" — [N] days overdue ([project])
NEXT MOVES (across all active projects)
[Project A]: [next_move]
[Project B]: [next_move]
PIPELINE
[N+1]. [next step]
[N+2]. [step after that]
...
[release step]: [what ships in the next release]
UNRESOLVED QUESTIONS (oldest/highest-priority)
⏰ [question older than 7 days — needs resolution]
? [question — blocking current step]
· [question — can wait]
PATTERNS REPEATING
~ [pattern detected across sessions]
═══════════════════════════════════════
Rules
- Sections only show if they have content — no empty sections
- Blockers first — if anything is blocked, show it before everything else
- Overdue decisions — always surface, never hide, use decision_review
- Next moves — call entity_read for all active entities, show each entity's next_move
- Aging rules for questions:
- ⏰ = older than 7 days unactioned
- blocking current plan step = show with ?
- backlog / can wait = show with ·
- max 5 questions total — oldest/highest-priority first
- Release queue = plan steps tagged with version numbers
- Patterns = call pattern_detect, show active patterns (skip if none)
- Keep it scannable — one line per item, no prose
- Never show entity IDs, decision IDs, or internal field names
- Write in plain language
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.
- 2d ago First seen · 81 lines · 0 tokens per session scan A c0232a2a096f
queue is a command published in the GitHub repository brainOS-HQ/brain-os (6 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 700 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
pm-arch
Scan project structure and generate Mermaid architecture diagrams + flowcharts under .pm/architecture/.
pm-done
Close a todo (TODO-xxx), sync completed.md, refresh overview.
pm-charter
Create, import, discover, approve, or skip project charter. No-arg form is an interactive wizard.
_closing
会改 .pm/ 的 /pm- 回复必须有一句中文摘要。链接只列已经存在的文件，不要指向还没生成的路径。.
tree-ring-certify
Generate Tree Ring harness or recall-quality evidence without confusing it with the full framework release suite.
tree-ring-recall
Recall durable Tree Ring Memory context before starting or resuming work.