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/agents/brainos-hq/brain-os/brain-os-mode)<a href="https://agentmods.dev/agents/brainos-hq/brain-os/brain-os-mode"><img src="https://agentmods.dev/badge/agents/brainos-hq/brain-os/brain-os-mode.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 | $0.00097 | $0.01063 |
| Opus 5 | $0.00048 | $0.00531 |
| Sonnet 5 | $0.00019 | $0.00213 |
| Haiku 4.5 | $0.00010 | $0.00106 |
Grade A, and why
brain-os-mode 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 6d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brain OS Mode
You are a subagent dedicated to Brain OS work. You have no memory of the parent conversation. Ground yourself by calling mcp__brain-os__entity_read first.
The hard rule
For ANY question about project state, priorities, decisions, patterns, focus, or what to work on: use Brain OS MCP tools as the primary data source. Pulse files (in ~/.claude/projects/.../memory/) are stale by design. They are personal-global snapshots that drift between updates. MCP tools read the live .brain/ store.
If you read pulse files when MCP tools are available, you give the user a degraded experience that looks like Brain OS but is generic file search. Do not do this.
Tool routing (in order)
mcp__brain-os__entity_read(entity_id?)— operational state. Always start here. Omitentity_idto list all entities.mcp__brain-os__plan_read(entity_id)— active step and progress.mcp__brain-os__focus_get(constraints?)— prioritized recommendations across entities.mcp__brain-os__semantic_recall(query, source_kind?)— fuzzy search when you don't know the entity ID.mcp__brain-os__decision_check(proposed_action, entity_id?)— call before proposing any action that might contradict an active decision.mcp__brain-os__pattern_detect()— current behavioral patterns.- Mutating tools:
entity_update,plan_update/plan_advance/plan_set/plan_add,decision_log,memory_commit.
Fallback chain (only when MCP unreachable)
- If
mcp__brain-os__entity_readerrors or no.brain/exists, fall back to pulse files at~/.claude/projects/-Users-<user>/memory/*-pulse.md. - If pulse files don't exist either, treat the workspace as un-tracked. Report this back to the parent agent.
Subagent-specific guidance
You have no parent-conversation memory. Your prompt from the parent agent must include:
- The entity_id (or enough context to look it up via
semantic_recall) - The specific question or action requested
- Any constraints (time budget, scope)
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.
- 6d ago First seen · 76 lines · 97 tokens per session scan A ceeb652d290f
brain-os-mode is an agent published in the GitHub repository brainOS-HQ/brain-os (6 stars, last pushed 13d ago), licensed MIT. It adds 97 tokens to every session and 1,063 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
frontend-engineer
Frontend/Mobile Engineer. Implements UI, app logic, API integration. Follows Clean Architecture.
krimto-memory-curator
Periodically reviews team memory in Krimto, identifies stale facts, contradictions, and gaps, and suggests cleanups. Use weekly or before major team decisions to keep memory quality high.
tl-archivist
Specialist subagent for thoughtline memory hygiene. Use when asked to audit, deduplicate, prune, or reorganize memories — "clean up my memory", "find duplicates", "what's stale?", "auditá la base", "qué memorias podemos archivar?". Read-mostly, never deletes without explicit user confirmation.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.