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/cleberfarias/devscope-mcp/architecturenpx skills add cleberfarias/devscope-mcp --skill architecturegit clone --depth 1 https://github.com/cleberfarias/devscope-mcpWhat 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 | $0.00028 | $0.00616 |
| Opus 5 | $0.00014 | $0.00308 |
| Sonnet 5 | $0.00006 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
architecture 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 2d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Architecture
Consultada quando o agente precisa descrever a arquitetura, stack ou estrutura de um
projeto. Assume que o contexto vem da ferramenta scan_project do mcp/server, que
retorna:
project_name, project_root, languages[], frameworks[], package_managers[],
test_frameworks[], infrastructure[], important_files[], confidence,
evidence[{file, reason, line?, excerpt?}]
Regras de decisão
-
Respeite o campo
confidence. Ele vale"high"só quando há evidência concreta (arquivo de manifesto encontrado ou dependência identificada);"medium"significa que a detecção veio só de extensões de arquivo, sem confirmação. Ao relatarconfidence: "medium", diga isso explicitamente — não apresente frameworks inferidos por extensão como fato consolidado. -
Toda afirmação sobre a stack deve citar
evidence. Sescan_projectdiz que o projeto usa React porque encontrou a dependência empackage.json, cite o arquivo. Seframeworkscontém algo sem entrada correspondente emevidence, foi inferido por heurística de extensão — trate com a mesma cautela do item 1. -
important_filesnão é a lista de todos os arquivos relevantes, é uma lista fixa de marcadores conhecidos (pyproject.toml,Dockerfile,.github/workflowsetc.). Ausência de um marcador na lista não prova que aquela tecnologia não existe no projeto — só que o scanner não tem heurística para ela ainda. Não conclua "este projeto não usa Docker" apenas porqueinfrastructurenão lista Docker; diga que o scanner não encontrou evidência, o que é diferente. -
package_managersmúltiplos (ex.:npmepipjuntos) é sinal de projeto poliglota ou monorepo, não de configuração inconsistente. Não sinalize isso como problema por padrão. -
languagesvem de extensão de arquivo, não de análise semântica. Um projeto com um único script.pyde automação dentro de um repositório majoritariamente TypeScript vai listar Python também. Ao resumir a stack principal do projeto, priorizeframeworksepackage_managers(que exigem evidência de manifesto) sobrelanguagessozinho.
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.
- 2d ago First seen · 53 lines · 28 tokens per session scan A f5ef66f89999
architecture is a skill published in the GitHub repository cleberfarias/devscope-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 616 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…