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/gitnpx skills add cleberfarias/devscope-mcp --skill gitgit 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 | $0.00024 | $0.00573 |
| Opus 5 | $0.00012 | $0.00287 |
| Sonnet 5 | $0.00005 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
git 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 yesterday.
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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Git
Consultada sempre que o agente precisa avaliar o estado de uma branch antes de
continuar uma tarefa ou abrir um Pull Request. Assume que o contexto vem da
ferramenta analyze_current_branch do mcp/server, que retorna:
branch, base_branch, ahead, behind, working_tree_clean,
changed_files[{path, status}], commits[{hash, message}], warnings[]
Regras de decisão
-
working_tree_clean == false— há alterações não commitadas. Não abra PR nem compare impacto até isso ser resolvido; pergunte ao usuário se quer commitar, descartar ou continuar mesmo assim. Nunca descarte automaticamente. -
behind > 0— a branch está atrás debase_branch. Trate como risco antes de qualquer análise de impacto: um diff calculado contra uma base desatualizada subestima o que realmente vai mudar quando a branch for integrada. Recomende atualizar a branch antes de prosseguir; não prossiga silenciosamente. -
ahead == 0echanged_filesvazio — não há trabalho para analisar. Não invente contexto; informe que não há diferença em relação à base. -
warningsnão vazio — sempre repita os avisos ao usuário em texto, mesmo que a tarefa continue. Um aviso descartado silenciosamente é o tipo de coisa que essa ferramenta existe para evitar. -
Leitura de
changed_files— o campostatussegue a convenção dogit diff --name-status(Aadicionado,Mmodificado,Ddeletado,R*renomeado). Arquivos com statusDnão devem ser tratados como "arquivos relacionados à tarefa" para efeito de busca de código — eles não existem mais na branch atual. -
commits— a mensagem de cada commit é a única evidência de intenção disponível nessa ferramenta. Se as mensagens não explicam o "porquê" de uma mudança emchanged_files, não presuma motivo — pergunte ou marque como desconhecido, em vez de gerar uma justificativa plausível mas não verificada.
Quando não usar
Se o diretório analisado não é um repositório Git, analyze_current_branch falha
com uma exceção antes de retornar esses campos — trate isso como ausência de
contexto de Git, não como branch limpa.
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.
- yesterday First seen · 51 lines · 24 tokens per session scan A e24734df337e
git is a skill published in the GitHub repository cleberfarias/devscope-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 573 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…