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 inhabitants/sapiens-mcp --skill repertoriogit clone --depth 1 https://github.com/inhabitants/sapiens-mcpWrote 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/inhabitants/sapiens-mcp/repertorio)<a href="https://agentmods.dev/skills/inhabitants/sapiens-mcp/repertorio"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/repertorio/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/inhabitants/sapiens-mcp/repertorio"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/repertorio.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 | $0.00063 | $0.00762 |
| Opus 5.5 | $0.00025 | $0.00305 |
| Sonnet 5.5 | $0.00013 | $0.00152 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
repertorio 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 26d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repertório: guardar obra e ferramenta no acervo
A regra que faz este fluxo falhar
Você NÃO grava uma obra passando o título. O servidor não aceita metadado vindo de você (título, capa, ano) de propósito: é anti-fabricação. Você identifica a obra num provider, e o servidor re-resolve por id e grava o canônico.
São sempre DOIS passos. Pular o primeiro falha sempre, e é o erro número um deste fluxo.
Guardar uma obra
action=resolvecommediaTypeequery(o título como a pessoa falou). Custo 0. Volta até 8 candidatos, cada um comsourceeexternalId.- Escolha o candidato certo. Em dúvida entre dois, PERGUNTE em vez de chutar: obra errada no acervo é a pessoa quem vai ter que apagar.
action=add_itemcom osourcee oexternalIdexatos daquele candidato, mais o que é pessoal:status,rating(0-10),tags,note,containsSpoilers,isPublic.
mediaType: movie, series, anime, game, book, music, tool, person, boardgame.
status: backlog (quer ver), active (vendo agora), completed (viu), paused, dropped.
Jogo de tabuleiro (e de cartas) é boardgame: game é videogame, e o provider dele não conhece tabuleiro. A busca do tabuleiro é na Wikidata e acha pelo título em inglês; o designer vem em authors no candidato e separa homônimos. Lançamento muito recente pode ainda não estar cadastrado: resolve vazio quer dizer que o jogo não está na base, então diga isso à pessoa.
Nunca invente um externalId nem reaproveite um de outra busca: id que não resolve no provider é rejeitado. A dedup é por (você, source, externalId), então repetir o mesmo par não duplica.
Guardar uma ferramenta de IA
Outro par, mesmo espírito: action=search_tools com query (catálogo aberto, custo 0, sem login) e depois action=add_tool com o toolId do candidato. Estar no acervo já quer dizer "usei"; favorite: true é o eixo separado de "curto e indico".
Ler o acervo
action=list e action=search exigem userId. Descubra uma vez com sapiens_meta action=whoami e reuse na conversa inteira. action=get pede itemId, que vem do list/search.
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.
- 26d ago First seen · 42 lines · 63 tokens per session scan A bb23b4554d19
repertorio is a skill published in the GitHub repository inhabitants/sapiens-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 762 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 2026-09-28.
Other skills, from other repositories
harness-design-fuzzing
Reference vocabulary for designing instrumented harnesses that drive vulnerability discovery — design classes (trigger-driven vs coverage-driven), tiered scope (T1 isolated function / T2 multi-component / T3 full build), systematic input exploration, the two-coverage distinction (fuzzer-feedback vs audit)…
memory-safety-c-cpp
Reference vocabulary for memory-safety vulnerabilities in native C/C++ code — bug-class taxonomy, common arithmetic patterns that lead to corruption, dispatch-family discipline, type-confusion idioms, use-after-free patterns, and exploitability factors. Read when analyzing, hypothesizing, designing harnesses for, or…
json-schema-emails
Canonical shape of the .workflow/emails/emails.json file passed between the fetch and summarize states — required fields (sender, recipient, subject, date, body), types, and field semantics. Read this whenever you write or read emails.json so producer and consumer agree on the shape.
mcptoon
Compress MCP tool discovery with the mcptoon CLI. Trigger when a session has a large MCP tool catalog (many servers/tools), when the user mentions token cost, tool discovery, mcptoon, or asks to list/call MCP tools efficiently. Also route here when the user says the MCP tool list is too large, the agent context window…
cortex-profile
View and manage your cognitive profile — how you think, work patterns, blind spots, and cross-domain connections. Use when the user says 'show my profile', 'how do I work', 'what are my patterns', 'cognitive style', 'blind spots', 'methodology', or at the start of a session to load context. Also use 'rebuild profile'…
linkding
Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.