Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/xiaojiou176-open/notes-recovernpx agentmods add skills/xiaojiou176-open/notes-recover/noteyard-case-reviewWrote 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/xiaojiou176-open/notes-recover/noteyard-case-review)<a href="https://agentmods.dev/skills/xiaojiou176-open/notes-recover/noteyard-case-review"><img src="https://agentmods.dev/badge/skills/xiaojiou176-open/notes-recover/noteyard-case-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/xiaojiou176-open/notes-recover/noteyard-case-review"><img src="https://agentmods.dev/badge/skills/xiaojiou176-open/notes-recover/noteyard-case-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 | $0.00022 | $0.00334 |
| Opus 5 | $0.00011 | $0.00167 |
| Sonnet 5 | $0.00004 | $0.00067 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
notes-recover-case-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 11d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- notes-recover-case-review — 100% identical, 0 lines differ
- notes-recover-case-review — 100% identical, 0 lines differ
What it actually says
NotesRecover Case Review
Use this skill when an agent is reviewing one NotesRecover case root or the public-safe demo surface.
Product truth
- Recovery is the main product.
- AI and MCP are review layers, not the recovery engine.
- Stay local, copy-first, and case-root-driven.
- Prefer derived artifacts before raw copied evidence.
- Do not treat the live Notes store as a target.
- Do not describe this repo as a hosted or multi-tenant platform.
Preferred evidence order
- Read
review_index.md. - Read the verification preview and pipeline summary.
- Use
notes-recovery ask-casefor one bounded operator question. - Use
notes-recovery case-diffonly when comparing two case roots. - Use
notes-recovery public-safe-exportwhen you need a shareable bundle.
Bounded MCP entry
notes-recovery-mcp --case-dir ./output/Notes_Forensics_<run_ts>
Proof path
notes-recovery demonotes-recovery ai-review --demonotes-recovery ask-case --demo --question "What should I inspect first?"notes-recovery doctor
Truth language
- Good: "repo-owned independent skill surface"
- Good: "local copy-first case review skill"
- Forbidden: "officially listed skill" without fresh host-side read-back
- Forbidden: "hosted Notes recovery platform"
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.
- 11d ago First seen · 47 lines · 22 tokens per session scan A 6af210cb4d5f
notes-recover-case-review is a skill published in the GitHub repository xiaojiou176-open/notes-recover (2 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 334 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
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.