What is bitbucket-review?

A shell-based tool for reviewing pull requests in Bitbucket Server, a self-hosted code collaboration service. It can inspect changes without first cloning the repository.

It helps read diffs and changed files, write review comments or inline findings, and prepare or publish a review decision.

It lets developers review a Bitbucket pull request from the command line without running a separate integration server or manually downloading the project.

bitbucket-review — Skill for Claude Code and Codex by cuonghuunguyen

Install

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.

Any agent

npx skills add cuonghuunguyen/bitbucket-mcp --skill skill

Clone the repo

git clone --depth 1 https://github.com/cuonghuunguyen/bitbucket-mcp

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cuonghuunguyen/bitbucket-mcp/skill/github.svg)](https://agentmods.dev/skills/cuonghuunguyen/bitbucket-mcp/skill)

Your own site

<a href="https://agentmods.dev/skills/cuonghuunguyen/bitbucket-mcp/skill"><img src="https://agentmods.dev/badge/skills/cuonghuunguyen/bitbucket-mcp/skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cuonghuunguyen/bitbucket-mcp/skill"><img src="https://agentmods.dev/badge/skills/cuonghuunguyen/bitbucket-mcp/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 188 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,445 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00188	$0.03445
Opus 5.5	$0.00075	$0.01378
Sonnet 5.5	$0.00038	$0.00689
Haiku 4.5	$0.00019	$0.00345

Measured 7d ago against content hash 0d2f3bcf4d1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bitbucket-review scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Do not fall back to `curl` against the REST API.

packages/skill/SKILL.md · 291 lines

How it starts

The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bitbucket review with the `bb` CLI

bb is a Bitbucket Server client for code review. Every command prints human-readable text by default and structured JSON with --json. Errors go to stderr as error: <message> with exit code 1.

Setup check (do this once per session, before anything else)

bb whoami
# User:       jsmith
# Instance:   https://bitbucket.example.com
# Auth:       access token
# Credential: environment

bb whoami is the setup check, not bb ping. bb ping calls /application-properties, which many Bitbucket Server instances answer 200 anonymously — so a successful bb ping proves only that the URL is right and the server is up, and will happily succeed with no credential at all. bb whoami calls a user-scoped endpoint and reports the authenticated username, so it is the only one of the two that proves you are authenticated. Use bb ping afterwards only to tell "server is down" apart from "credential is wrong".

If bb whoami succeeds, you are configured and can start work. If it fails:

bb: command not found — bb is not on PATH. Build and link the CLI: pnpm --filter @cuonghuunguyen/bitbucket-cli build && pnpm --filter @cuonghuunguyen/bitbucket-cli link --global. Do not fall back to curl against the REST API.
No Bitbucket Server URL configured / '…' is not a valid Bitbucket Server URL — no instance is configured. Export BITBUCKET_URL, or pass --url.
Not logged in to <url> / Authentication failed (401) — there is no usable credential. See the rule below: ask the user, do not try to log in.

Credentials are resolved in this order, highest precedence first:

--url / --token flags on the command
BITBUCKET_URL / BITBUCKET_TOKEN in the environment, or in a .env in the working directory
the credential the user stored earlier with bb login, in the OS keyring

Never run `bb login` yourself

bb login is interactive. It prompts for the instance URL, then for a token or a username and password, and it refuses to run at all without a TTY. It is not something to run unattended, and it is never a step you should attempt on the user's behalf — you would either hang waiting on a prompt or fail outright.

Read the full file on GitHub · 291 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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 Changed 0d2f3bcf4d1a
1mo ago Changed e679458de2f4
2mo ago First seen · 291 lines · 188 tokens per session scan A 01db1101412b

Subscribe to this mod's changes

bitbucket-review is a skill published in the GitHub repository cuonghuunguyen/bitbucket-mcp (1 stars, last pushed 9d ago), licensed ISC. It adds 188 tokens to every session and 3,445 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review

bitbucket-review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bitbucket-reviewcuonghuunguyen/bitbucket-mcp	Skill	1	9d ago	ISC	A	188	Claude Code, Codex
autoreviewopenclaw/clawhub	Skill	9.5k	today	MIT	A	17	Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills	Skill	2.2k	6d ago	MIT	A	115	Claude Code, Codex
omh-code-reviewrlaope/oh-my-hermes	Skill	5.2k	today	MIT	A	48	Claude Code, Codex
revdiff-planumputun/revdiff	Skill	947	2d ago	MIT	A	84	Claude Code
explore-unknownsdzhng/skills	Skill	1.4k	today	MIT	A	162	Claude Code, Codex
re0-mergeLilMGenius/paperthin	Skill	1.4k	4d ago	MIT	A	70	Claude Code

bitbucket-review