Borrowing it
Nothing to install: this file belongs to novasamatech/nova-spektr. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/novasamatech/nova-spektr/dev/.claude/skills/search-patterns/SKILL.mdgit clone --depth 1 https://github.com/novasamatech/nova-spektrWrote 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/novasamatech/nova-spektr/search-patterns)<a href="https://agentmods.dev/skills/novasamatech/nova-spektr/search-patterns"><img src="https://agentmods.dev/badge/skills/novasamatech/nova-spektr/search-patterns/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/novasamatech/nova-spektr/search-patterns"><img src="https://agentmods.dev/badge/skills/novasamatech/nova-spektr/search-patterns.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 | $0.00076 | $0.00472 |
| Opus 5.5 | $0.00030 | $0.00189 |
| Sonnet 5.5 | $0.00015 | $0.00094 |
| Haiku 4.5 | $0.00008 | $0.00047 |
Grade A, and why
search-patterns scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Search Patterns
The canonical convention is docs/content/docs/code/style/search.md — read it before writing or changing any list
search. Core rule: the query matches the strings the user actually sees in the row, never raw stored fields.
Operational rules
- Engine:
performSearchfrom@/shared/lib/utils(weighted substring match,getMetafor computed display strings). Never hand-roll.toLowerCase().includes()filters for user-facing search. - Account lists: use
accountService.searchAccountsfrom@/domains/network. It matches resolved account name (useAccountsNames), resolved wallet name (useWalletsNames) and the displayed SS58 address. Reference usage:src/renderer/features/multisig-wallet-create/*/components/components/Signatory.tsx; tests:src/renderer/domains/network/account/service.test.ts(searchAccountsblock). - Rows rendered via
<NamedAccount>/useAccountName/useWalletName⇒ the same resolved names must be in the search meta. If the component displays${walletName} (${accountName}), both parts must be searchable. - Do not re-rank lists whose order carries meaning (validators by stake, operations by date) — filter over displayed strings but keep the source order.
- Effector-model searches (no React hooks available) must still search displayed strings — resolve names via
accountService.resolveAccountName/ domain caches, not rawwallet.name/account.name.
Review checklist
When reviewing a diff that touches search:
- Find what the row renders (which name/address, with what prefix).
- Find what the query is matched against.
- Any displayed string missing from the match set, or any matched field that is never displayed — flag it.
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.
- 2mo ago First seen · 36 lines · 76 tokens per session scan A e726b5b57ea3
search-patterns is a skill published in the GitHub repository novasamatech/nova-spektr (55 stars, last pushed yesterday), licensed Apache-2.0. It adds 76 tokens to every session and 472 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-01.
search-patterns compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| search-patternsnovasamatech/nova-spektr | Skill | 55 | yesterday | Apache-2.0 | A | 76 | Claude Code |
| implementerparitytech/polkadot-ios-community | Skill | 5 | yesterday | GPL-3.0 | A | 26 | Claude Code |
| architectparitytech/polkadot-ios-community | Skill | 5 | yesterday | GPL-3.0 | A | 27 | Claude Code |
| reviewerparitytech/polkadot-ios-community | Skill | 5 | yesterday | GPL-3.0 | A | 27 | Claude Code |
| commit-messageparitytech/polkadot-ios-community | Skill | 5 | yesterday | GPL-3.0 | A | 14 | Claude Code |
| blockchain-web3j4flmao/agent-skills | Skill | 38 | 3d ago | MIT | A | 128 | Claude Code, Codex |
| frontend-designrylsherdamz-rgb/stellar-forge | Skill | 17 | 5d ago | MIT | A | 51 | Claude Code |