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/proggarapsody/bitbottle/skillsnpx skills add proggarapsody/bitbottle --skill skillsgit clone --depth 1 https://github.com/proggarapsody/bitbottleWrote 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/skills/proggarapsody/bitbottle/skills)<a href="https://agentmods.dev/skills/proggarapsody/bitbottle/skills"><img src="https://agentmods.dev/badge/skills/proggarapsody/bitbottle/skills.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 | $0.00084 | $0.03509 |
| Opus 5 | $0.00042 | $0.01754 |
| Sonnet 5 | $0.00017 | $0.00702 |
| Haiku 4.5 | $0.00008 | $0.00351 |
Grade A, and why
bitbottle 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 6d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bitbottle CLI
A gh-style CLI for Bitbucket Server/DC and Cloud. This file is a router
plus invariant safety rules — load the matching reference for command
detail. Don't memorize this file; run bitbottle <cmd> -h for the
authoritative shape and flag list. Run bitbottle --version if behavior
disagrees with this doc; the binary wins.
When to load which reference
| Task | Open |
|---|---|
Auth, hosts.yml, env vars, multi-host, auth migrate, auth doctor |
references/auth.md |
| PR lifecycle (list/view/create/merge/merge-preview/approve/comment/activity/review/commits/files/participants/ready/unready/task/suggestion/comment-react/default-reviewer/reviewer-group/…) | references/pr.md |
Repos, branches, tags, file/tree, visibility, edit, transfer, watcher, repo label list/create/update/delete, repo pr-settings get, repo pr-settings set, repo download list/upload/get/delete, repo clone (MCP: clone_repo), repo hook list/view/enable/disable/settings get/set (Server/DC only), repo sync Cloud fork sync (MCP: sync_repo) |
references/repos.md |
| Commits (log, search, view/files/status/comment/comment-react) | references/commit.md |
| Pipelines, pipeline config get/enable/disable, schedules, caches, watch, trigger, test-report view, test-case list, SSH key pair, known hosts, OIDC config/keys (Cloud only) | references/pipeline.md |
| Pipeline runners — list / create / delete (Cloud only) | references/runner.md |
| Code Insights reports/annotations (Cloud + Server/DC); merge-check (Server/DC only) | references/code-insights.md |
| Issues, comments, attachments (list/delete), vote/unvote, watch/unwatch, activity/change log (Cloud only) | references/issues.md |
| Issue milestones list/view (Cloud only) | references/milestone.md |
| Issue versions list/view/create/delete (Cloud only) | references/version.md |
| snippet list/view/create/delete, snippet comment list/add/delete (Cloud only) | references/snippet.md |
| Deployments + environments + variables (Cloud only) | references/deployment.md, references/variable.md |
| Deploy keys (both), branch-rules (Cloud only), ssh-keys (Cloud + Server/DC) | references/deploy-key.md, references/branch-rule.md, references/ssh-key.md |
Diff between refs, diff REF1..REF2 |
references/diff.md |
Branch compare (branch compare BASE..HEAD) — ahead/behind counts + commit lists (Cloud + Server/DC) |
references/branch.md |
Workspaces + webhooks + workspace project CRUD + workspace project perms + workspace perms + workspace pipeline variables (Cloud only), user view |
references/workspace.md, references/user.md |
| Mirror servers (list/view/repo list) (Server/DC only) | references/mirror.md |
Named credential profiles (profile create/use/list/delete) |
references/profile.md |
| Raw REST passthrough, pagination, MCP server config | references/api.md |
Extensions (extension install/list/upgrade/remove/exec, extension scaffold) |
references/extension.md |
| Group management — group list, group create, group delete, group member list, group member add, group member remove (Server/DC only) | references/groups.md |
| Project CRUD — project server-list, project create, project view, project edit, project delete (Server/DC only); project list WORKSPACE (Cloud only) | references/project.md |
| auth pat list/create/revoke (Server/DC only) | references/auth.md |
Host info — backend type, base URL, version, feature matrix (host info [--json]) |
references/host.md |
What ships with it
34 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.
- agents/openai.yaml 431 B
- references/admin.md 5.8 KB
- references/api.md 2.1 KB
- references/auth.md 6.0 KB
- references/branch-model.md 2.6 KB
- references/branch-rule.md 3.4 KB
- references/branch.md 1.4 KB
- references/code-insights.md 1.2 KB
- references/commit.md 7.2 KB
- references/deploy-key.md 2.2 KB
- references/deployment.md 2.7 KB
- references/diff.md 2.3 KB
- references/extension.md 1.0 KB
- references/groups.md 2.0 KB
- references/host.md 1.4 KB
- references/issues.md 2.6 KB
- references/milestone.md 715 B
- references/mirror.md 1.4 KB
- references/perms.md 5.2 KB
- references/pipeline-cache.md 1.6 KB
- references/pipeline.md 14 KB
- references/pr.md 14 KB
- references/profile.md 1.7 KB
- references/project.md 2.7 KB
- references/repos.md 13 KB
- references/runner.md 2.3 KB
- references/snippet.md 4.7 KB
- references/ssh-key.md 1.8 KB
- references/user.md 988 B
- references/variable.md 3.6 KB
- references/version.md 1.2 KB
- references/workspace.md 11 KB
- scripts/sync_help.py 4.9 KB runs code
- scripts/test_sync_help.py 5.2 KB runs code
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.
- 6d ago First seen · 214 lines · 84 tokens per session scan A caa5f4ef1fac
bitbottle is a skill published in the GitHub repository proggarapsody/bitbottle (3 stars, last pushed 18d ago), licensed MIT. It adds 84 tokens to every session and 3,509 once invoked, about $0.0004 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
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
cherry-pick
Cherry-pick a commit from main to a Sui release branch, create the release PR, and report the PR URL.
task-snapshot
Create a commit or tag snapshot only when explicitly requested for a milestone, reproducibility checkpoint, handoff, or pinned artifact.
mflux-pr
Make a clean PR in mflux (inspect diff, quick verification, commit, push, open PR) using repo conventions.
comet-safe-delivery
在保护无关脏改动、关联 worktree、子模块和用户明确边界的前提下，提交、推送、合并或完成范围明确的 Comet 变更。用户要求提交、推送、合并回目标分支、清理 worktree 或交付已准备好的改动时使用。.
changelog
Auto-generates a changelog from git commits, sprint data, and design documents. Produces both internal and player-facing versions.