crew-change
The change-request template, the ten questions a change board requires, and how each field maps onto ServiceDesk Plus, Jira and a local file.
Skill by mbadali25
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mbadali25-crew-change
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/crew-change
What's inside
- Skill name
crew-change- Description
- The change-request template, the ten questions a change board requires, and how each field maps onto ServiceDesk Plus, Jira and a local file. Use when filing, checking or closing a change request, when a production promotion asks for an approved change, or when the user says change request, change management, CAB, change window, rollback plan or post-change validation.
- License
- GPL-2.0
- Instructions
- 187 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Change requests
One process, three backends. The wording lives here and nowhere else:
`commands/change.md` reads this file, and the gate that enforces it is
`hooks/scripts/crew_change.py`. Three copies of a question list is two copies
that drift, and they drift in the direction of being shorter.
---
## 1. The template
The ServiceDesk Plus **Change Management Request** template is the shape all
three backends carry. Jira and files mode reproduce it exactly; the only thing
that differs between backends is where the text lands.
| Field | Where it comes from |
|---|---|
| Priority | asked per request |
| Impact | asked per request |
| Urgency | asked per request |
| Impact Details | asked per request — the blast radius in prose, not a repeat of Impact |
| Requester name | asked per request |
| Implementor of Change | asked per request — and it is also answer 2 |
| Scheduled Start Time | asked per request — and it is also part of answer 3 |
| Scheduled End Time | asked per request — and it is also part of answer 3 |
| Subject | asked per request |
| Category | asked per request |
| Description | the ten answers in §2, in order, verbatim question then answer |
`Requester name` and `Implementor of Change` are asked every time: no config
key holds them. Everything else is per-request too: a default Priority is a
Priority nobody chose.
**Scheduled Start Time and Scheduled End Time are the change window**, and they
are not decoration. When `change.requireForProduction` is true they are what
`/crew:promote production` checks the clock against.
---
## 2. The ten questions, verbatim
The template prints this above them, and it is the whole reason the gate
exists:
> ALL THE BELOW QUESTIONS MUST BE ANSWERED. ANY PERTINENT MISSING INFORMATION
> WILL RESULT IN THE REQUEST BEING DENIED.
1. What specifically is the change?
2. Who will be implementing the change (added to Requestor Details also)?
3. What is the scheduled time for the change - list downtime duration and
day/time (added to Requestor Details also)?
4. Who will this change affect? (how many are affected, what areas, or how
many users)
5. What is the worst-case scenario of impact to end users?
6. What systems/applications are affected? (IP address, URL and/or hostname)
7. List the system/applications/services impact, and whether each impacted
system/application/service is hosted locally or in the cloud
8. What is your rollback plan?
9. Has there been a notification sent to those affected?
10. Attach results of post-change validation
**Questions 2 and 3 are answered twice on purpose** — once here, and once in
Requestor Details, because that is what the template asks for. Say the same
thing in both places rather than abbreviating one of them.
---
## 3. The gate
`hooks/scripts/crew_change.py` owns it. Run it; do not judge the answers by
reading them.
```
python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/crew_change.py --answers <file.json> --mode new
python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/crew_change.py --answers <file.json> --mode close
```
- `--mode new` gates **questions 1–9**. Exit 0 means every one has a real
answer. Exit 2 means it refused, and stderr names each failing question and
says whether the box was empty or held a placeholder.
- `--mode close` gates **question 10 only**. The other nine were gated at
filing and the backend holds them.
- **Any non-zero exit is a refusal, including one caused by unreadable input.**
The two states that must never be confused are "complete" and "could not
tell", so everything that is not a verified pass exits non-zero.
The placeholder list is `crew_change.PLACEHOLDERS` and it is **not repeated
here** — a second copy is a copy that drifts. Two of its judgement calls are
worth knowing while you collect answers: a bare `none` is refused (say "no
users are affected: the service has no consumers yet" instead, which is what a
change board wants anyway), and a bare `no` is accepted, because it is a
complete answer to question 9.
Question 10 is answered at `close`, never at `new`: at filing time the change
has not happened, so requiring it would make the gate unsatisfiable and the
natural repair would be to type `N/A` — which teaches an operator that
placeholders are how you get past this gate.
---
## 4. Field mapping per backend
The **content is identical in all three**. Only the transport differs.
### ServiceDesk Plus (`tracker: "sdp"`)
Reached through the `sdp_*` MCP tools, the same ones `/crew:sdp-sync` and the
`infra-work-ticketing` skill use. Filed with `sdp_create module=change`.
| Template field | SDP |
|---|---|
| — | `template` = `Change Management Request` (fixed: `crew_state.CHANGE_SDP_TEMPLATE`) |
| Subject | `subject` |
| Priority / Impact / Urgency / Category | resolve each against `sdp_list_metadata` **first** |
| Impact Details | `impact_details` |
| Requester name | `requester` |
| Implementor of Change | `change_owner`, and repeated in the description as answer 2 |
| Scheduled Start / End Time | `scheduled_start_time` / `scheduled_end_time` |
| Description | the ten Q&A pairs, question then answer, in order |From mbadali25/useful-claude-add-ons, GPL-2.0.
More from mbadali25/useful-claude-add-ons
- 0.603score
crew-qa-standards
mbadali25
Harness, QA-review and environment standards plus a report-only audit (parallel tests, pinned linters CI really runs, gate rules that can fail, QA environment…
SkillAFreshness: A★ 2Claude Code +9 - 0.603score
crew-graph
mbadali25
Build and query a code graph of this repository with graphify, keeping it on the filesystem as graph.json and fresh on commit.
SkillAFreshness: A★ 2Claude Code +9 - 0.603score
crew-best-practices
mbadali25
Community best practices for working with Claude Code - context management, planning, TDD, hooks, skills, subagents, slash commands and MCP - with what crew…
SkillAFreshness: A★ 2Claude Code +9 - 0.599score
crew-diagrams
mbadali25
Author architecture, process, sequence, ER and data-flow diagrams as Mermaid that pass a measured readability check (no crossing lines, nothing drawn through…
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
crew-providers
mbadali25
Set up, verify, and invoke external model providers - Codex, Kimi Code or GitHub Copilot for QA review, Gemini for design second opinions.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
crew-context
mbadali25
Manage context exhaustion - warn near the limit, write handoff notes, and resume work after a clear or compact.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
crew-debugging
mbadali25
Find the cause of a defect before proposing a fix - read errors, reproduce, check recent changes, gather evidence from this repo's code map and verification…
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
crew-memory
mbadali25
Conventions for durable project memory across repos, including Obsidian vault integration.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
crew-notify
mbadali25
Set up outbound notifications to Microsoft Teams or Telegram - deploy results and "Claude stopped and is waiting" questions - and explain the two-way MCP…
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
crew-cloud
mbadali25
Configure the official AWS and Azure MCP servers safely for a repo.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
crew-docs
mbadali25
Keep CHANGELOG.md, README.md, SECURITY.md, TODO.md, ADRs, generated docs, and the API and feature reference current as work lands.
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
crew-brainstorm
mbadali25
Turn a request into an approved direction before it becomes a spec - one question per message, options with the recommendation first, never implement before…
SkillAFreshness: A★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 17
- Last commit (this folder)
- Sep 25, 2026 (1 month ago)
- Last release
- Jul 28, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- GPL-2.0
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mbadali25
- 0.603score
crew-graph
mbadali25
Build and query a code graph of this repository with graphify, keeping it on the filesystem as graph.json and fresh on commit.
SkillAFreshness: A★ 2Claude Code +9 - 0.603score
crew-qa-standards
mbadali25
Harness, QA-review and environment standards plus a report-only audit (parallel tests, pinned linters CI really runs, gate rules that can fail, QA environment…
SkillAFreshness: A★ 2Claude Code +9 - 0.603score
crew-best-practices
mbadali25
Community best practices for working with Claude Code - context management, planning, TDD, hooks, skills, subagents, slash commands and MCP - with what crew…
SkillAFreshness: A★ 2Claude Code +9 - 0.599score
crew-diagrams
mbadali25
Author architecture, process, sequence, ER and data-flow diagrams as Mermaid that pass a measured readability check (no crossing lines, nothing drawn through…
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
crew-debugging
mbadali25
Find the cause of a defect before proposing a fix - read errors, reproduce, check recent changes, gather evidence from this repo's code map and verification…
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
crew-context
mbadali25
Manage context exhaustion - warn near the limit, write handoff notes, and resume work after a clear or compact.
SkillAFreshness: A★ 2Claude Code +9
Cite this page
crew-change skill. Agent Mart. https://agentmart.dev/skills/mbadali25-crew-change (last updated 2026-10-24)