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/deevus/tea-skills/create-pullnpx skills add deevus/tea-skills --skill create-pullgit clone --depth 1 https://github.com/deevus/tea-skillsWrote 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/deevus/tea-skills/create-pull)<a href="https://agentmods.dev/skills/deevus/tea-skills/create-pull"><img src="https://agentmods.dev/badge/skills/deevus/tea-skills/create-pull.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 | $0.00030 | $0.00493 |
| Opus 5 | $0.00015 | $0.00246 |
| Sonnet 5 | $0.00006 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
create-pull 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 3d 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.
What it actually says
Create Pull Request
Use tea pulls create for pull request creation. Bundled actions are only for CLI gaps and are documented under actions/pull-requests/README.md.
When resolving actions/... paths, use the actions/ directory bundled relative to this skill directory.
Pass explicit scope flags (--login, --remote, or --repo) to bundled actions when the user names a login, remote, backend, or repository. Otherwise, bundled actions use active-host-first discovery.
Create
tea pulls create # interactive, current branch -> default branch
tea pulls create --title "Add auth" --description "Implements JWT" \
--head "feature/auth" --base "main" \
--labels "bugfix" --assignees "sh" --milestone "v1.0"
tea pulls create --head "contributor:feature-branch" --base "main" # from fork
WIP PR Convention
Use the normal tea CLI and prefix the title with WIP: when a Forgejo/Gitea workflow treats WIP titles as draft-like pull requests.
tea pulls create --title "WIP: Feature" --head feature-branch
tea pulls create --title "WIP: Feature" --head feature-branch --base develop
Quick Pattern
# PR from current branch
git push -u origin HEAD
tea pulls create --title "$(git log -1 --format=%s)" --head "$(git branch --show-current)"
Rediscover Created PR
tea pulls create output is human-oriented. When you need the created PR number or URL for automation, use the structured branch lookup action instead of parsing command output:
actions/pull-requests/find-by-branch.py
actions/pull-requests/find-by-branch.py --head "$(git branch --show-current)"
actions/pull-requests/find-by-branch.py --head "contributor:feature-branch" --base main
The action emits one JSON object per matching pull request as JSONL, suitable for jq or direct agent parsing.
What ships with it
1 file 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.
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.
- 3d ago First seen · 54 lines · 30 tokens per session scan A 6651e4cf6c2a
create-pull is a skill published in the GitHub repository deevus/tea-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 493 once invoked, about $0.0002 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
docs
This is the project knowledge base. It covers the conventions, workflows, and principles you need to work on gitea-mcp-server. Everything here is available directly — no skill loading required.
today-drink-tea
根据当前日期、时间、季节,从用户家茶叶库存中推荐"今天喝什么",输出400ml壶泡法(只泡一泡、茶水分离、TDS20纯净水)的投茶量、水温、浸泡时间。当用户问"今天喝什么""推荐一款茶""喝哪款"时触发;问"今天冷泡什么""冷泡推荐"时输出1.6L冷泡壶方案(投茶量、冷藏时长、可饮时间);用户说"XX太淡/太苦/涩"等喝感反馈时复盘调参,说"XX仓气重/仓味/堆味/霉味"或"洗茶太过/香味洗掉"时调整洗茶档位,说"XX闷味/闷熟"或"XX香气散/跑香"时调整盖盖/开盖,说"XX泡酸/发酸"或"XX香味没了/没香气"时降低水温(见"复盘调校"节);说"我搬到了外地"时清空全部库存(随后"我买了XX、YY、ZZ"批量导入自己的茶单);说…
git-forge-migration
Migrate repos between git forges (GitHub/Gitea/Codeberg).
git-flow
Větvení, checkpointy a odevzdání práce přes agenticdev-git.
kontext
Načte kontext klienta z prd/ — glosář, požadavky, rozhodnutí.
rozhodnuti
Zapíše architektonické rozhodnutí jako ADR a pošle ho na VPS.