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 skills add mycelium-hq/ai-brain-starter --skill optimize-braingit clone --depth 1 https://github.com/mycelium-hq/ai-brain-starterWrote 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/mycelium-hq/ai-brain-starter/optimize-brain)<a href="https://agentmods.dev/skills/mycelium-hq/ai-brain-starter/optimize-brain"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/optimize-brain/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mycelium-hq/ai-brain-starter/optimize-brain"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/optimize-brain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 529 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
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 | $0.00049 | $0.04954 |
| Opus 5 | $0.00024 | $0.02477 |
| Sonnet 5 | $0.00010 | $0.00991 |
| Haiku 4.5 | $0.00005 | $0.00495 |
Grade B, and why
optimize-brain scanned grade B with 1 finding 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 9d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/settings.local.json | grep -q "UserPromptSubmit" && echo "Hook installed" || echo "MISSING" How it starts
The opening of the file, as written. The whole thing — 599 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize Brain — Deep Vault Optimization
{SKILL_DIR}= this skill's own folder (locally: the directory this SKILL.md lives in; a served brain substitutes the real absolute path before you read this). Shared starter files live at the repo root two levels up:{SKILL_DIR}/../... If a path does not resolve, name the missing file and stop — never guess another location.
You are running a deep optimization on an existing Obsidian vault. The user has already set up the basics (folder structure, CLAUDE.md, context layer) — either through /setup-brain or manually. Now they want the full treatment.
This is a weekend project, not an afternoon one. Set expectations upfront and let them choose which phases to run.
Your tone: collaborative, methodical, honest about what takes time. You're a vault architect, not a setup wizard.
Opening
Start with:
"Hey! This is the deep optimization pass. Unlike setup, this one works with what you already have — your existing notes, journals, contacts, and files.
Here's what we can do. Each phase is independent — pick the ones that matter to you, or we can do them all:
- File Audit — scan your vault, report what's there, find the mess (10 min)
- AI Chat Import & Cleanup — export and import your ChatGPT/Claude/Gemini history, keep the gold, delete the noise (30-60 min)
- CRM Standardization — turn scattered people mentions into queryable contacts (30-60 min)
- Journal Compression — create monthly summaries from your journal entries (30-60 min)
- Domain Summaries — one compressed note per life area (20-30 min)
- Graph Cleanup — fix broken links, connect orphans, add missing links (20-30 min)
- Dashboards — build live Dataview queries for contacts, tasks, projects (15-20 min)
- Wikilink Audit — scan for people, concepts, and themes that should be linked but aren't (20 min)
- About Me / Then vs Now — build a self-portrait from your data (15 min)
- Skill & Routing Health Check — verify all skills work, paths resolve, CLAUDE.md routing is complete (10 min)
- Vault Health Report — final audit with stats and recommendations (10 min)
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.
- 9d ago First seen · 599 lines · 49 tokens per session scan B 71513a103962
optimize-brain is a skill published in the GitHub repository mycelium-hq/ai-brain-starter (36 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 4,954 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
flow
Personal task and agent-session manager. CLI binary is flow (assumed on PATH) and stores metadata in /.flow/flow.db (SQLite). Use this skill when the user asks about their work, tasks, or projects in any natural phrasing — including but not limited to: "what's left", "what's remaining", "what's pending", "what do I…
daily-brief
Compose a morning briefing for the user by pulling today's calendar, open tasks, and relevant memory, then delivering a short prioritized summary over the primary chat channel. Use when the user asks for a daily brief, "what's on today", a standup, or sets up a scheduled morning digest.
tg-slot
Free a membership slot so a Telegram account can join or create a group. Accounts have a hard ceiling on channels plus supergroups, and at the ceiling both creating and joining fail with an error that misleadingly blames the target chat. Finds the least-valuable current memberships, proposes what to leave, and retries…
claudeai-sync
Pull new and changed claude.ai web conversations into an Obsidian vault, extract artifacts as first-class notes, concept-link them, and refresh the RAG index and dashboard. Idempotent: curated notes are never overwritten. Triggers: "/claudeai-sync", "pull claude.ai", "grab new claude.ai chats".
gmail
Check, search or digest Gmail across several mailboxes over the owner's own OAuth connector, with no browser and near-zero tokens for the raw pull. Read-only by default: drafting and sending go through the outbound approval gate. Triggers: "/gmail", "check mail", "any important emails", "find the email about ".
tg-post
Publish a vetted post to one of your own Telegram channels or supergroups over the MCP connector rather than a browser, with the channel resolved strictly by id from a registry, rate-guarded and draft-first. It never posts to a chat matched by name similarity. Triggers: "/tg-post", "publish to the telegram channel".