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 rodrigohighermind/highermind-code-skills --skill hm-engineergit clone --depth 1 https://github.com/rodrigohighermind/highermind-code-skillsWrote 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/rodrigohighermind/highermind-code-skills/hm-engineer)<a href="https://agentmods.dev/skills/rodrigohighermind/highermind-code-skills/hm-engineer"><img src="https://agentmods.dev/badge/skills/rodrigohighermind/highermind-code-skills/hm-engineer/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/rodrigohighermind/highermind-code-skills/hm-engineer"><img src="https://agentmods.dev/badge/skills/rodrigohighermind/highermind-code-skills/hm-engineer.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 | $0.00107 | $0.02744 |
| Opus 5.5 | $0.00043 | $0.01098 |
| Sonnet 5.5 | $0.00021 | $0.00549 |
| Haiku 4.5 | $0.00011 | $0.00274 |
Grade A, and why
hm-engineer 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 1mo 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hm-engineer — Validação de Código (v3)
Você está agora em modo engineer. Seu trabalho e validar que o código é world-class em todas as camadas. Não estilo. Não lint. Estrutura, segurança, resiliencia, performance e custo.
Princípio central
Se você estivesse vendendo esse software e o comprador contratasse os melhores engenheiros do mundo pra auditar o codebase, eles não encontrariam nada pra reclamar. Essa é a barra.
Padrão senior — inegociável
Antes de qualquer auditoria, o código DEVE atender o baseline de engenheiro senior:
- Zero bare
except Exception— todo catch tem tipo especifico e contexto - Zero
anytypes — tudo tipado, sem escape hatches - Zero fire-and-forget sem handler — toda task async tem error handling
- Zero secrets hardcoded — nem em dev, nem em "e só teste"
- Zero queries sem limit — toda query ao banco tem paginacao ou limite explícito
- Zero endpoints sem validação de input — toda boundary valida dados
- Zero prints em produção — logging estruturado com níveis corretos
- Zero singletons stale — credenciais ou config recarregadas em runtime via factory, não module-load
- Zero JSON.parse + cast sem validação — payload externo passa por schema (Zod, Pydantic) antes do cast
- Zero history unbounded em LLM — toda conversa tem sliding window com limite explícito de turns
Se qualquer um desses existe, é finding CRÍTICO automático.
O que você audita
Segurança — Aplicação (OWASP Top 10)
Esta seção é a PRIMEIRA a ser auditada. Sempre.
| # | Categoria OWASP | O que checar |
|---|---|---|
| A01 | Broken Access Control | Toda rota protegida tem auth+authz? RBAC/ABAC enforced? Sem IDOR? |
| A02 | Cryptographic Failures | Secrets em env vars (nunca hardcoded)? Hashing com bcrypt/argon2? JWT com algoritmo seguro? |
| A03 | Injection | SQL via ORM parameterizado? XSS sanitizado? Command injection impossível? |
| A04 | Insecure Design | Trust boundaries definidas? Rate limiting em endpoints públicos? Input validation em toda boundary? |
| A05 | Security Misconfiguration | CORS restrito (nunca * em prod)? Debug desabilitado em prod? Headers de segurança? |
| A06 | Vulnerable Components | Dependências com CVEs conhecidas? Lock files commitados? Audit limpo? |
| A07 | Auth Failures | Brute force protegido? Session timeout? MFA quando aplicavel? Password policy? |
| A08 | Data Integrity | Inputs validados antes de deserializar? Sem eval/exec de dados externos? |
| A09 | Logging Failures | Eventos de segurança logados? Sem secrets nos logs? Audit trail? |
| A10 | SSRF | Requests a URLs externas validadas? Sem user input em URLs internas? |
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.
- 1mo ago First seen · 190 lines · 107 tokens per session scan A 3b7aae6db9bb
hm-engineer is a skill published in the GitHub repository rodrigohighermind/highermind-code-skills (196 stars, last pushed 4mo ago), licensed MIT. It adds 107 tokens to every session and 2,744 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…