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 coachinggit 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/coaching)<a href="https://agentmods.dev/skills/mycelium-hq/ai-brain-starter/coaching"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/coaching/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/coaching"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/coaching.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00103 | $0.03098 |
| Opus 5 | $0.00051 | $0.01549 |
| Sonnet 5 | $0.00021 | $0.00620 |
| Haiku 4.5 | $0.00010 | $0.00310 |
Grade A, and why
coaching 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 10d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coaching Session — Multi-Pass Panel + Accountability Tracking
A skill that turns a one-off hard moment into a tracked accountability arc. Runs panel passes that update with the user's corrections, files a synthesized record with a re-eval date, and updates the vault's rolling pattern tracker so growth can be measured over time.
Why this exists
Daily journals capture one moment per day. Panel reactions inside /journal are one-shot. Most real coaching, real therapy, real advisor relationships are NOT one-shot — they're multi-turn, they update when new evidence comes in, and they track whether the same blind spot keeps surfacing across months.
The vault has all the pieces (panel rules in ⚙️ Meta/rules/advisory-panel.md, daily journals, decision logs) but no skill that orchestrates the multi-pass coaching arc and files it for tracking. This skill fills that gap.
Three-tier architecture
This skill produces files at three different timescales:
-
Verbatim raw (immediate) —
📋 Strategy/Coaching Sessions/Processing Notes - YYYY-MM-DD - <topic>.md. The user's exact words during the session. Per the "save exact words" rule, no annotation, no synthesis. Available for re-read forever. -
Synthesized accountability record (per session) —
🏠 Home/Coaching Sessions/YYYY-MM-DD - <topic>.md. What surfaced, commitments named, re-eval date one month out. This is the file/weeklyand/monthlylook at to ask "did the pattern repeat? did the commitments land?" -
Rolling pattern aggregator (across sessions) —
🏠 Home/Panel Feedback Log.md. Patterns table at the top tracks mention counts. Single mention = watch. 2+ mentions across different contexts = promote to acute action item. The aggregator is what tells you "this is a real recurring pattern" vs "this was a one-off."
All three tiers honor __SKIP. Coaching sessions are exactly where someone says something out loud to think about it, not to record it. Before writing any of the three files, strip every line whose first token is __SKIP, then confirm one line per dropped item (Dropped __SKIP line N (token preview: ...)). Never paraphrase the dropped content into the synthesized record — tier 2 summarizing what tier 1 was told not to keep is the exact leak the convention exists to stop. Enforced by block-skip-prefix-in-vault-write.py; full rule at templates/rules/skip-prefix-convention.md.
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.
- 10d ago First seen · 236 lines · 103 tokens per session scan A e47ab3a43772
coaching is a skill published in the GitHub repository mycelium-hq/ai-brain-starter (36 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 3,098 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 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".