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 agentmods add skills/trycomp-io/comp-skills/research-digestnpx skills add trycomp-io/comp-skills --skill research-digestgit clone --depth 1 https://github.com/trycomp-io/comp-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/trycomp-io/comp-skills/research-digest)<a href="https://agentmods.dev/skills/trycomp-io/comp-skills/research-digest"><img src="https://agentmods.dev/badge/skills/trycomp-io/comp-skills/research-digest.svg" alt="Measured on agentmods" 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 | $0.00174 | $0.02203 |
| Opus 5 | $0.00087 | $0.01102 |
| Sonnet 5 | $0.00035 | $0.00441 |
| Haiku 4.5 | $0.00017 | $0.00220 |
Grade A, and why
research-digest 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 5d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dual-mode operation (Code + Cowork)
HTML through the design system (required). Whenever this skill produces HTML, load the
comp-html-guidelinesskill first and apply the CompDS design system. This holds even when the user does not ask to "style it" or "make it look good" — every HTML output from this skill goes through the design system. It does not change the methodology below; it only governs the HTML's visual layer.
Detect platform at start:
- If you have the
Bashtool AND can run Python → use script mode (the 3-step workflow below:fetch_research.pydoes multi-source dedup against OpenAlex/arXiv/RSS, you translate,generate_digest.pyrenders the HTML). Deterministic and higher-recall. - Otherwise (e.g., Claude Cowork web, no Python) → use inline mode (the "Inline curation logic" section): curate via web search using the same theme keywords, translate to PT-BR, output a markdown digest. If an HTML artifact tool is available, ALSO render the digest as a self-contained HTML artifact matching the 3-zone layout below.
Both modes cover the same 3 themes, the same 12-week window, and the same editorial rules (translate everything to PT-BR, mark paywalls, prefer frontier over canon, no marketing fluff, no invented content).
Inline curation logic (Cowork mode)
No Python in Cowork, so you cannot run the multi-source fetcher. Curate with the web search tool instead, best-effort, signal over recall.
Step 1: Search each theme (last ~12 weeks). Use these keyword sets:
- Org Design: "organizational design", "span of control", "delayering", "team topologies", "agile organization"
- Workforce Planning: "strategic workforce planning", "skills-based organization", "internal mobility", "talent forecasting", "human capital strategy"
- IA & Força de Trabalho: "generative AI" + ("productivity" OR "workforce" OR "labor"), "LLM" + ("occupation" OR "task"), "AI exposure", "future of work" + AI
Prioritize: working papers/preprints (arXiv, SSRN, NBER), peer-reviewed studies, and consultancy reports WITH primary data or disclosed methodology. Exclude pure marketing and one-off explainers. Aim for ~5-10 high-signal items per theme; quality over quantity.
What ships with it
7 files 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.
- 5d ago First seen · 148 lines · 174 tokens per session scan A 7b4ffcab5edd
research-digest is a skill published in the GitHub repository trycomp-io/comp-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 174 tokens to every session and 2,203 once invoked, about $0.0009 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
contingencia-report
Gera relatórios estruturados de contingência jurídica para uso em balanços, auditoria e compliance. Use quando o usuário precisar classificar processos por probabilidade de perda (provável/possível/remota) conforme CPC art. 95-96 e IAS 37 / CPC 25, calcular impacto financeiro no passivo contingente, ou preparar…
contrato-review
Analisa contratos brasileiros identificando cláusulas problemáticas, riscos jurídicos e oportunidades de negociação. Use quando precisar fazer due diligence contratual, revisar minutas antes de assinatura, identificar cláusulas abusivas ou desequilibradas, verificar conformidade com CC/2002, CDC, LGPD ou legislação…
audiencia-classifier
Classifica publicações de audiência judicial por tipo e modalidade. Use quando receber textos de intimações, pautas de audiência ou publicações do diário de justiça e precisar categorizar automaticamente em INICIAL/INSTRUÇÃO/JULGAMENTO/CONCILIAÇÃO × PRESENCIAL/VIRTUAL/HÍBRIDA. Aplicável a publicações de qualquer…
Triagem e Resposta a Solicitações de Titulares (LGPD)
Classifica solicitações de titulares de dados pessoais recebidas pelo canal de privacidade, verifica prazo legal de resposta, identifica o direito exercido (Art. 18 LGPD) e gera minuta de resposta formal adequada ao pedido.
cnj-parser
Valida, normaliza e extrai componentes de números de processos judiciais brasileiros no formato CNJ (NNNNNNN-DD.AAAA.J.TT.OOOO). Use quando receber números de processo em formatos variados (com ou sem máscara, colados de sistemas diferentes), precisar validar dígitos verificadores, identificar tribunal, instância e…
Geração de RIPD (Relatório de Impacto à Proteção de Dados)
Gera o Relatório de Impacto à Proteção de Dados Pessoais (RIPD) conforme exigido pela LGPD (Art. 38), descrevendo o tratamento, identificando riscos, propondo medidas de mitigação e documentando a base legal aplicável.