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 mrDesign-ww/vault-os --skill evolution-verifiergit clone --depth 1 https://github.com/mrDesign-ww/vault-osWrote 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/mrdesign-ww/vault-os/evolution-verifier)<a href="https://agentmods.dev/skills/mrdesign-ww/vault-os/evolution-verifier"><img src="https://agentmods.dev/badge/skills/mrdesign-ww/vault-os/evolution-verifier/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/mrdesign-ww/vault-os/evolution-verifier"><img src="https://agentmods.dev/badge/skills/mrdesign-ww/vault-os/evolution-verifier.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 | $0.00039 | $0.00758 |
| Opus 5 | $0.00019 | $0.00379 |
| Sonnet 5 | $0.00008 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
evolution-verifier 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 7d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evolution Verifier
Проведи независимую read-only проверку предложения или подготовленного diff. Ничего не меняй и не запускай команды, которые пишут данные.
Проверка
- Сформулируй цель и перечисли затронутые файлы.
- Прочитай полный diff и контекст затронутых файлов.
- Проверь:
- zone isolation и корректную маршрутизацию PARA;
- отсутствие несанкционированной отправки данных или сетевых вызовов;
- атомарность state-файлов и использование wiki-lock для пакетных правок;
- сохранность append-only
log.mdи источников вsources/; - обратимость и понятный recovery path;
- локальные воспроизводимые доказательства;
- соответствие exact standing reflection policy, manifest и scan receipt;
- точное равенство reviewed checkpoint diff: один parent, exact current HEAD, полный sorted список path + SHA-256 без удалений, merge или посторонних файлов;
- checkpoint меняет только exact materialized outcome pages из signal plan. Shared
wiki/index.md,wiki/log.md,wiki/hot.md,wiki/overview.md, project_index.mdи generated index в автономный checkpoint не входят; - после outcome-only checkpoint acceptance выполняется под тем же work-lock token. Locked retrieval проверяет exact локальный index authority без требования к текущему HEAD; обычный retrieval без token по-прежнему требует checkpointed authority и отказывает во время записи;
- generated authority фиксируется только последующим обычным metadata-checkpoint после durable finalization. Он не расширяет reviewed outcome diff;
- для каждой materialized страницы exact frontmatter provenance: manifest SHA-256, scan receipt SHA-256 и JSON-список назначенных signal IDs;
- L0 evidence не трактуется как прямое одобрение.
- Классифицируй находки: BLOCKER, HIGH, MEDIUM, LOW.
- Выдай один вердикт: PASS, REVISE или BLOCK.
Не исправляй найденное сам. Передай конкретные file:line и минимальную правку основному агенту.
При PASS выдай content-free JSON plan schema 2. Он обязан содержать только поля schema_version, verdict, platform, policy_sha256, manifest_sha256, scan_receipt_sha256, verifier, checkpoint, signals. verifier содержит name: evolution-verifier, verdict: PASS и exact SHA-256 этого skill. checkpoint содержит exact parent_sha, commit_sha и sorted changed_paths, где каждый элемент имеет только path и committed blob sha256. signals отсортирован по signal_id; rejected содержит только signal_id и action, materialized дополнительно exact page_path. Не добавляй quotes, transcript text или summary в plan.
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.
- 7d ago First seen · 36 lines · 39 tokens per session scan A cc578993a2d7
evolution-verifier is a skill published in the GitHub repository mrDesign-ww/vault-os (2 stars, last pushed 5d ago), licensed MIT. It adds 39 tokens to every session and 758 once invoked, about $0.0002 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 2026-09-05.
Other skills, from other repositories
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".