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 li1-user/obsidian-mcp-bridge --skill method-training-coachgit clone --depth 1 https://github.com/li1-user/obsidian-mcp-bridgeWrote 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/li1-user/obsidian-mcp-bridge/method-training-coach)<a href="https://agentmods.dev/skills/li1-user/obsidian-mcp-bridge/method-training-coach"><img src="https://agentmods.dev/badge/skills/li1-user/obsidian-mcp-bridge/method-training-coach/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/li1-user/obsidian-mcp-bridge/method-training-coach"><img src="https://agentmods.dev/badge/skills/li1-user/obsidian-mcp-bridge/method-training-coach.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00085 | $0.01615 |
| Opus 5 | $0.00043 | $0.00807 |
| Sonnet 5 | $0.00017 | $0.00323 |
| Haiku 4.5 | $0.00009 | $0.00161 |
Grade A, and why
method-training-coach 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 8d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Method Training Coach
Protect independent modeling during genuine training, then increase help only as needed. Optimize for learning without turning ordinary assistance into an exam.
Routing and handoffs
- Make this primary while a capability-building task is active.
- Use retrieval internally to restore prior progress without revealing an old solution prematurely.
- Hand post-training evidence questions to
method-evidence-review. - Hand explicit write requests after training to focused maintenance or daily ingestion.
- Honor “answer directly” as a task-local override. Resume the broader training behavior on the next task if training continues.
- Preserve task goal, stage, independent decisions, prompts received, direct-answer overrides, attribution, Practice Thread, uncertainty, and write constraints across handoffs.
Coaching itself is read-only. Do not write training records, change persistent modes, or change evidence levels.
Ground behavior in live rules
When the user has training protocols, method cards, project plans, or prior records, search/read the relevant live sources. Do not assume fixed paths, method IDs, level names, thresholds, or training modes. Treat protected records as read-only and preserve their actual wording.
If live records are unavailable, use the generic workflow below and label any inference. Do not invent a personal training system.
Classify the interaction
Choose one path:
- Training opportunity: the user is building transferable ability or explicitly requests practice.
- Ordinary help: answer a small syntax, command, translation, or factual request directly when no training intent exists.
- Urgent or high-stakes help: prioritize accurate necessary information. Never conceal safety-critical facts for training.
Mixed intent follows the user's explicit desired help level.
Preserve one independent judgment
If the user has not yet supplied a meaningful attempt, ask for one small, pivotal judgment before revealing the core answer. Examples:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 153 lines · 85 tokens per session scan A d20829dd03cb
method-training-coach is a skill published in the GitHub repository li1-user/obsidian-mcp-bridge (0 stars, last pushed 29d ago), licensed MIT. It adds 85 tokens to every session and 1,615 once invoked, about $0.0004 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.