Borrowing it
Nothing to install: this file belongs to jacobpixleratgather/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/jacobpixleratgather/bitbucket-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/jacobpixleratgather/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/jacobpixleratgather/bitbucket-mcp/agents-md)<a href="https://agentmods.dev/instructions/jacobpixleratgather/bitbucket-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jacobpixleratgather/bitbucket-mcp/agents-md/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/instructions/jacobpixleratgather/bitbucket-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jacobpixleratgather/bitbucket-mcp/agents-md.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 | $0.03258 | $0.03258 |
| Opus 5 | $0.01629 | $0.01629 |
| Sonnet 5 | $0.00652 | $0.00652 |
| Haiku 4.5 | $0.00326 | $0.00326 |
Grade A, and why
bitbucket-mcp AGENTS.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 4d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repository guidelines for agents
This file is the source for CLAUDE.md and .cursor/rules/viteplus.mdc (both symlink here). Edit this file; the symlinks follow automatically.
What this project is
bitbucket-mcp is a stdio Model Context Protocol server for Bitbucket Cloud. It exposes 15 tools to MCP hosts (Claude Code, Claude Desktop) for reading PR diffs, reading/writing PR comments (including inline file+line comments), creating PRs, editing the PR Overview (title + description), toggling draft/ready state, resolving and unresolving comment threads, finding Pipelines builds and reading their step logs, checking a commit's build status, and triggering a build.
It's distributed on npm as @mcpkits/bitbucket. Users run npx -y @mcpkits/bitbucket setup once for OAuth + Claude Code registration; the server is then loaded transparently by their MCP host on each invocation.
The design doc is at docs/superpowers/specs/2026-04-20-bitbucket-mcp-design.md — read it before making architectural changes. The pipeline-discovery and output-size behaviour is specified separately in docs/superpowers/specs/2026-08-18-pipeline-discovery-and-output-limits-design.md.
Three invariants worth knowing before touching the auth, pipeline or diff paths:
- Never report "no pipeline" when pipelines exist. Bitbucket abbreviates a PR's
source.commit.hashto 12 chars while a pipeline'starget.commit.hashis the full 40, so commits must be compared by prefix (commitMatches), never by string equality — that bug made every PR look like it had no pipeline.list_pipelinesalso falls back to the PR's source branch when nothing is attributable to the PR, and returns amatchdiscriminator (pr_head_commit/branch_fallback/none) plus anote. An empty list must only ever mean "nothing ran". - The refresh token rotates, so credentials are shared state. Spending a refresh token retires it, and the config file is the only copy - other server processes and scripts that borrow these credentials (the webapp's
pr-dash) read and write the same file. Every refresh therefore runs underwithRefreshLock, spends the newest refresh token on disk rather than the one read before queueing, and takes a pair another process stored instead of rotating again. A failed refresh only clears the tokens when the token on disk is still the one that just failed: a refresh token that changed underneath us means someone else's refresh succeeded, and wiping it would log every session out over a lost race. - Every unbounded response is capped. PR diffs and step logs both carry a
max_bytesdefault and a narrowing argument (paths/stat_only,tail_lines). A truncated response always says so and says how to narrow it.
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.
- 4d ago Changed · +1 lines · +143 tokens per session 590e8161bd72
- 9d ago First seen · 211 lines · 3,115 tokens per session scan A bf4d08f5c004
bitbucket-mcp AGENTS.md is an instructions file published in the GitHub repository jacobpixleratgather/bitbucket-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 3,258 tokens to every session, about $0.0163 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).
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.
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.