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 skills/sandeep84397/agent-brain/brain-compilernpx skills add sandeep84397/agent-brain --skill brain-compilergit clone --depth 1 https://github.com/sandeep84397/agent-brainWrote 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/skills/sandeep84397/agent-brain/brain-compiler)<a href="https://agentmods.dev/skills/sandeep84397/agent-brain/brain-compiler"><img src="https://agentmods.dev/badge/skills/sandeep84397/agent-brain/brain-compiler.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 | $0.00017 | $0.00206 |
| Opus 5 | $0.00009 | $0.00103 |
| Sonnet 5 | $0.00003 | $0.00041 |
| Haiku 4.5 | $0.00002 | $0.00021 |
Grade A, and why
brain-compiler 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 5d 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.
What it actually says
Brain compiler
Read {{CONTRACT_PATH}} completely before any action. Treat it as normative;
do not redefine SAN semantics in this skill.
Use only Agent Brain MCP tools inherited from the current host:
- Call
get_roadmap,pre_check, andlog_decisionfor one bounded batch. - Call
plan_san_refresh; read only source files returned as missing or stale. - Apply all contract parity checks before publication.
- Call
publish_sanonce per validated source and never write.sandirectly. - Call
log_outcome; report paths, counts, and validation metadata only.
If the configured model is unavailable, stop before generation and report no fallback. Do not invoke Claude, Anthropic APIs, another host, or any external provider subprocess. Never send source or SAN content outside inherited Agent Brain publication tools.
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.
- 5d ago First seen · 23 lines · 17 tokens per session scan A c85fae34371c
brain-compiler is a skill published in the GitHub repository sandeep84397/agent-brain (10 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 206 once invoked, about $0.0001 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 skills, from other repositories
claude-api
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…
agent-coordination
Find other agents, list participants in a conversation, send routed messages, attach files, and recover earlier conversation context (history / resolve a fuzzy reference / read a quoted message / read compressed summaries). Use whenever you need to delegate to another agent, address a peer in a multi-agent…
image-generate
Generate an image from a text prompt via the cloud LLM image proxy, persist it as a content-addressed workspace asset, and return a ContentBlock that downstream renderers can attach. Use whenever the user asks "draw / generate / make an image of …", an agent needs a diagram / illustration as a follow-up artifact, or a…
prismer-im-collab
Coordinate reliably in Prismer conversations, use workspace assets through bounded MCP tools, and keep task work on the board.
claim-agent-ownership
Orchestrator skill for resolving multi-daemon binding contention. Use when you (the orchestrator) detect an agent.binding.contested sync event indicating two daemons are racing for the same agent — explicitly rebind ownership to a chosen target daemon so subsequent dispatches route deterministically. Implements Gap…
assets
Locate, inspect, and read content-addressed workspace assets — search by filename/metadata, describe before reading bytes, then read bounded ranges. Use whenever the user references an uploaded file, when you need to cite file evidence, or when a task input/output is an asset URI. Executes via the cloud asset CLI and…