Borrowing it
Nothing to install: this file belongs to marcusyoda/bitbucket-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/marcusyoda/bitbucket-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/marcusyoda/bitbucket-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/instructions/marcusyoda/bitbucket-mcp/claude-md)<a href="https://agentmods.dev/instructions/marcusyoda/bitbucket-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/marcusyoda/bitbucket-mcp/claude-md.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 5.1 | $0.01082 | $0.01082 |
| Opus 5 | $0.00541 | $0.00541 |
| Sonnet 5 | $0.00216 | $0.00216 |
| Haiku 4.5 | $0.00108 | $0.00108 |
Grade A, and why
bitbucket-mcp CLAUDE.md 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 7d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md, bitbucket-mcp
Regras deste projeto. Seguir à risca. Ao trabalhar neste repo ou ao operar o MCP em qualquer projeto, respeitar tudo abaixo.
O que é
MCP server (TypeScript, ESM, stdio) pro Bitbucket Cloud. Existe porque o MCP oficial da Atlassian cobre só Jira + Confluence, não o Bitbucket. Dá superfície de tools controlada e payloads enxutos pra PRs, código, branches, pipelines, webhooks e variáveis, em vez de chamada solta na REST API.
Auth: Atlassian API token scoped, Basic email:token. Workspace e repo vêm das env
(BITBUCKET_WORKSPACE, BITBUCKET_DEFAULT_REPO), sem default embutido.
Regras de segurança (à risca)
- Scopes do token: exatamente os 8 de PERMISSIONS.md. Nunca pedir
nem assumir
admin:*oudelete:*sem decisão humana explícita registrada em PERMISSIONS.md. Tools de variável dão 403 sem admin: isso é esperado, não é bug, não tentar contornar. - Branches protegidas (
BITBUCKET_PROTECTED_BRANCHES, defaultmain,dev) nunca são mutadas direto.git_push,git_rebase,delete_branch,create_branchrecusam mirar elas, e confirm NÃO fura isso. Mudança pra main/dev só via PR. merge_pull_requestpara main/dev é permitido, mas só comconfirm:true. É o caminho sancionado.- Ações destrutivas exigem
confirm:true:merge,decline,delete_*,stop_pipeline,git_commit,git_push, comentário inline (add_pr_commentcominline_path), criar variávelsecured. BITBUCKET_READ_ONLY=truebloqueia todo write/destrutivo antes de tocar a API. Usar em sessões de só leitura (review, drift, conferência).- Valores de variável secured nunca são retornados nem logados (write-only na API).
git_*/cloneusam a chave SSH, não o token. Push pra protegida é bloqueado em 3 camadas: guarda do MCP + branch restrictions server-side + sem rebase de branch protegida.
Convenções
- Sem travessão nem meia-risca em nenhum texto: código, commits, comentários de PR, docs. Usar vírgula, dois pontos, parênteses ou quebra de linha.
- Comentário de PR: texto em português + Conventional Comments. Label em inglês, corpo em
PT. Ex:
**suggestion (non-blocking):** extrair isto pra um helper. Labels: praise, nitpick, suggestion, issue, todo, question, thought, chore, note. - Estilo de código: pnpm, ESM, strict TS, single quotes, semicolons, width 100, build tsup ESM.
- Mensagem de commit: conventional, assunto curto, sem em dash.
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.
- 7d ago First seen · 69 lines · 1,082 tokens per session scan A c73b7033c970
bitbucket-mcp CLAUDE.md is an instructions file published in the GitHub repository marcusyoda/bitbucket-mcp (1 stars, last pushed today), licensed MIT. It adds 1,082 tokens to every session, about $0.0054 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.