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-evidence-reviewgit 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-evidence-review)<a href="https://agentmods.dev/skills/li1-user/obsidian-mcp-bridge/method-evidence-review"><img src="https://agentmods.dev/badge/skills/li1-user/obsidian-mcp-bridge/method-evidence-review/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-evidence-review"><img src="https://agentmods.dev/badge/skills/li1-user/obsidian-mcp-bridge/method-evidence-review.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 | $0.00091 | $0.01523 |
| Opus 5 | $0.00046 | $0.00762 |
| Sonnet 5 | $0.00018 | $0.00305 |
| Haiku 4.5 | $0.00009 | $0.00152 |
Grade A, and why
method-evidence-review 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Method Evidence Review
Assess method growth from traceable behavior after training. Recommend; never auto-upgrade, auto-downgrade, check a level box, or write the recommendation into the Vault.
Routing and evidence access
- Make this primary for explicit evidence, attribution, practice-count, progress, transfer, or level-readiness questions.
- Use retrieval tools internally to gather current method definitions, level meanings, project records, problem records, training traces, and summaries.
- Let
method-training-coachlead an active exercise. Review only completed portions at a real boundary. - Hand accepted evidence facts to
obsidian-note-maintenanceordaily-knowledge-ingestonly when the user requests writing. - Evidence approval is semantic approval, not confirmation of a later unseen Patch.
- Preserve task-local goal, stage, source references, overrides, attribution, Practice Thread, uncertainty, and write constraints across handoffs.
Do not assume fixed method IDs, levels, folder names, or thresholds. Re-read the user's live method record and level policy. If unavailable, state what cannot be determined.
Build Evidence Units in reasoning
Analyze each candidate through:
- method or strategy;
- Practice Thread;
- context and domain;
- trigger;
- autonomy;
- action;
- result;
- transfer;
- first-hand source.
Do not create a new schema or one file per Evidence Unit. These dimensions prevent messages, commits, stages, and Agent calls from becoming fake practice counts.
Attribute each meaningful decision
user-independent: without a current Agent prompt for the method, the user recognizes the situation and performs the key behavior.user-prompted: after a clear directional prompt, the user performs it correctly.agent-executed: the Agent performs the main judgment, design, or implementation; user approval does not change the actor.
Attribute decisions separately. A task can contain independent, prompted, and agent-executed parts. When actor or prompting is unclear, mark it unknown or disputed. Never infer attribution from project name, note tone, stage name, or general collaboration.
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.
- 10d ago First seen · 141 lines · 91 tokens per session scan A 0a82c29f2900
method-evidence-review is a skill published in the GitHub repository li1-user/obsidian-mcp-bridge (0 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 1,523 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
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.