Close Milestone Agent Skill

Closes a milestone whose work is complete — verifies that all its issues are closed (paginated and against the tracker counts) and that…

Context cost
4k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 15.9 kBtext throughout, nothing executable
Licence
not declarednone named by its author
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Zavře milestone, jehož práce je hotová — ověří, že všechna jeho issues jsou zavřená (stránkovaně a proti počtům z trackeru) a že integrační PR je opravdu zmergovaný, a teprve pak milestone zavře jedním voláním. Při jakémkoli rozporu nezavírá a vypíše, co brání: otevřená issues i s čísly, nezmergované PR, nebo anomálii. Prázdný milestone nezavírá tiše.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

collaboration

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md15.9 kB · preview
--- name: close-milestone when_to_use: >- Použij, když je práce na milestonu hotová a má se uzavřít — „zavři milestone", „ukliď hotový milestone", „je to zmergované, zavři to" — typicky poté, co člověk zmergoval integrační PR do výchozí větve. Nepoužívej pro zavírání jednotlivých issues, to je jedno volání trackeru, ne úloha pro skill; ani pro plánování milestonu, na to slouží plan-milestone; ani pro posouzení plánu, to dělá review-milestone; ani pro implementaci jeho issues, tu řídí run-milestone — ten milestone záměrně nechává otevřený, protože finální merge patří člověku. argument-hint: "[název nebo číslo milestonu]" model: haiku # Effort tu není a být nesmí: haiku ho nepodporuje a jeho uvedení skončí chybou # při běhu (model-effort-matrix.md, Tabulka 1 a Časté chyby). Není to opomenutí. # Zařazení dle matice: inventura a kontrola formátu → haiku, bez effortu. # Postup je proto vědomě držený mechanický: každé rozhodnutí v krocích 1–3 je # vyjmenované jako podmínka nad hodnotou z trackeru (počty sedí/nesedí, PR má # merge/nemá, shoda názvu je/není) a v žádné mezní situaci skill nezavírá podle # vlastního úsudku — nejednoznačnost vždy končí otázkou na uživatele. Nikoli # sonnet: nic se tu nenavrhuje ani neposuzuje. Kontextový limit haiku (200K) # nevadí, skill čte výpisy trackeru, ne dokumentaci projektu. Kdyby reálné běhy # ukázaly, že haiku některou z větví míjí, správnou opravou je sonnet × medium # (bod 2 rozhodovacího stromu), ne dopisování dalších podmínek. user-invocable: true allowed-tools: - Read - AskUserQuestion - ToolSearch - "Bash(bash:*)" - mcp__gitea__milestone_read - mcp__gitea__milestone_write - mcp__gitea__list_issues - mcp__gitea__list_pull_requests - mcp__gitea__pull_request_read # Zúžení práv je tu levné a smysluplné: skill má jediný zápis (zavřít milestone) # a všechno ostatní jen čte. Bash je zúžený na spouštění skriptů; git ani gh se # nikdy nevolá přímo. Proto volání skriptů piš ve tvaru # `bash "${CLAUDE_PLUGIN_ROOT}/scripts/gh/<skript>.sh"` — v jiném tvaru buď # nespadne do povolení, nebo se v izolovaném worktree netrefí do kořene pluginu. # ToolSearch a pětice mcp__gitea__* je tu kvůli Gitea # větvi: nástroje jsou odložené a bez ToolSearch se nenačtou, bez uvedení v tomto # výčtu se nezavolají. Názvy odpovídají tvaru z forge-recipes.md; běží-li Gitea # MCP pod jiným prefixem, ohlas to a výčet neobcházej. # Vynechaná zvažovaná pole: effort — viz výše, u haiku je to chyba za běhu; # Glob/Grep — konfigurace má pevnou cestu a zbytek vstupu jsou výpisy trackeru, # není co hledat v souborech; Write/Edit — skill nezapisuje na disk; # disable-model-invocation — zavření je vratné jedním voláním a cíl si skill # nevybírá sám (krok 1), takže samovolné spuštění nemůže zavřít nic cizího; # context/agent/background — výběr milestonu i potvrzení mezních stavů potřebují # uživatele v hlavním kontextu, fork ani běh na pozadí nemají komu klást otázky; # paths — spouští se z konverzace, ne prací nad soubory; shell — skripty se # spouští explicitním `bash`; disallowed-tools — allowed-tools je uzavřený # výčet, není co zakazovat navíc; version/license — verzuje se celý plugin. ---
62# Close Milestone
63
64Cílem je zavřít milestone teprve tehdy, když je jeho práce **prokazatelně**
65hotová — všechna issues zavřená a integrační PR zmergovaný. Zavřít předčasně je
66horší než nezavřít: zavřený milestone vypadá jako hotová práce a nikdo se do něj
67už nedívá. Závazným kontraktem jsou sdílené soubory pluginu; při rozporu s tímhle
68postupem platí ony.
69
70| Soubor | Kdy ho otevři |
71| --- | --- |
72| ${CLAUDE_PLUGIN_ROOT}/shared/workflow-config.md | V kroku 1, když projektová konfigurace chybí nebo v ní nenajdeš sekci, kterou potřebuješ |
73| ${CLAUDE_PLUGIN_ROOT}/shared/forge-recipes.md | V kroku 1, dřív než sáhneš na tracker — včetně sekce s nástrahami, na které tenhle skill stojí |
74| ${CLAUDE_PLUGIN_ROOT}/shared/git-scripts.md | V kroku 1, je-li forge GitHub — než spustíš první gh/*.sh |
75
76## Vstupní kontext
77
78- Milestone od uživatele (může být prázdné): $ARGUMENTS
79
80## Postup
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md2,190 words
Files1
Licencenot declared
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈890
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
3,085
on trigger
The instruction body, read only when the skill fires.
2.0%
of a 200k window
Ten skills this size would take about 20% of the window before you open a file.
050k100k150k200k context window

4k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Middling. Fine to keep on in a project where you use it weekly, worth unloading in one where you never do.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md asks for Bash, which can write files and reach the network alike, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

The allowed-tools line of this skill’s own SKILL.md asks for Bash, which could do either, so neither is ruled out. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 15.9 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md15.9 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Close Milestone · 4k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/close-milestone/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/close-milestone" ] && { [ ! -e .claude/skills/close-milestone ] || { mv .claude/skills/close-milestone "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/close-milestone" .claude/skills/ && echo "Installed .claude/skills/close-milestone"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add sagittaras/close-milestone

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/close-milestone/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/close-milestone/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/close-milestone" ] && { [ ! -e ~/.claude/skills/close-milestone ] || { mv ~/.claude/skills/close-milestone "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/close-milestone" ~/.claude/skills/ && echo "Installed ~/.claude/skills/close-milestone" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/close-milestone/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencesagittaras/close-milestone

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

SA
sagittaras

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill