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/graphgit 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 | $0.00720 |
| Opus 5 | $0.00000 | $0.00360 |
| Sonnet 5 | $0.00000 | $0.00144 |
| Haiku 4.5 | $0.00000 | $0.00072 |
Grade A, and why
graph 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brain OS : Entity Graph
Show how entities connect, what they share, and where building one helps another.
REQUIRED FIRST READ
Before any tool call, read ~/.claude/brain-os/PROTOCOL.md.
Input
Arguments: $ARGUMENTS (optional : an entity name for its connections, or "full" for the complete graph)
Primary tool sequence
mcp__brain-os__entity_read(): all entities and theirrelated_entitiesfieldsmcp__brain-os__pattern_detect(): shared themesmcp__brain-os__semantic_recall(query, source_kind="decision"): cross-entity decisions
If entity name given : connections view
Read the named entity plus all entities it relates to.
========================================
[ENTITY NAME] : CONNECTIONS
========================================
DEPENDS ON
----------------------------------------
[entity] : [what this entity needs from that one]
FEEDS INTO
----------------------------------------
[entity] : [what that entity gets from this one]
SHARES WITH
----------------------------------------
[entity] : [architecture, patterns, users, or theme]
SHARED DECISIONS
----------------------------------------
[decision that affects multiple connected entities]
========================================
LEVERAGE INSIGHT
========================================
[one sentence: if you work on X, it also advances Y because Z]
========================================
If "full" or no argument : full graph
Display all entities grouped by strategic theme, showing connections.
================================================
ENTITY GRAPH
================================================
[THEME 1 : e.g. SHARED FOUNDATION]
--------------------------------------------
[entity A] -> [entity B] : [why]
[THEME 2 : e.g. CONSUMER APPS]
--------------------------------------------
[entity C] <-> [entity D] : [shared concern]
[PARKED / ARCHIVED]
--------------------------------------------
[names, comma-separated]
================================================
HIGHEST LEVERAGE NODE
--------------------------------------------
[which entity, if advanced, creates the most
downstream value across other entities?]
SHARED ARCHITECTURE OPPORTUNITIES
--------------------------------------------
[what could be built once and reused?]
CROSS-ENTITY DECISIONS PENDING
--------------------------------------------
[decisions that affect more than one entity]
================================================
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 · 102 lines · 0 tokens per session scan A 314a6f952909
graph 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 720 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
start-feature
Command "start-feature" from melagiri/code-insights, covering /start-feature — auto-setup feature development team, step 1: create git worktree, example (adapt the slug from $arguments), step 2: create named team and step 3: spawn pm agent.
taskstoissues
基于现有设计制品，将任务转换为可执行、带依赖顺序的 GitHub Issues。.
pm-outline
Generate detailed project outline and draft charter from user intent (empty/new projects).
show-status
作用: 显示当前 PaperFit 任务的运行状态、缺陷消除进度、视觉优先级、修复计划摘要和下一步行动；这是当前默认的“摘要 / 解释”入口。.
implement-issue
Command "implement-issue" from outfitter-dev/blz, covering implement linear issue, context, important, preparation and workflow sequence.
status
Show current project state and task status.