linktrend/ide-development/git-safeguard
Claude Code and agent skill by linktrend/ide-development
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Applies a mandatory safety checklist before git push operations to prevent accidental or unsafe repository publication.
Install
npx vskill@latest install linktrend/ide-development/git-safeguardSKILL.md
The same SKILL.md was published earlier as linktrend/ide-development/git-safeguard.
git-safeguard
Profile: `simple`. This is a single-pass, stateless safety gate. It carries no taskledger, no{{task_id}}state machine, and no resumable multi-phase workflow — it runs amandatory checklist once per push and returns a decision. Telemetry (the Phase 5 ledgerappend) is still mandatory.
Preconditions (Fail-Fast)
- Intelligence floor check: confirm the active runtime satisfies
frontmatter.engine. - Tooling policy check: plan must follow the CLI-first protocol below.
- Confirm a concrete push target (branch + remote) is provided; otherwise stop and request it.
Safety Checklist (Mandatory Before git push)
- Run
git statusand verify intended branch/files only. - Run
git diff --cachedand review exact staged content. - Confirm no prohibited artifacts or secrets are staged.
- Confirm branch naming policy and remote target.
- Only then permit
git push. Block the push on any unresolved checklist item and report the exact remediation.
Tooling Protocol (CLI-First)
- Level 1 - Native CLI: native cli commands (
git status,git diff --cached) are primary. - Level 2 - CLI Wrapper Scripts: a cli wrapper under
scripts/may automate checklist execution. - Level 3 - Direct API: direct api is exception-only.
- Level 4 - MCP: mcp applies only to persistent session operations.
- When the skill is Generalist or has >10 tools, call
get_tool_detailsand cache capability summaries before use.
Ledger (Telemetry — mandatory)
On completion, append { "timestamp", "skill", "task_id", "status", "summary" } to the root execution_ledger.jsonl. Telemetry is required for every skill regardless of profile. task_id here is a lightweight ledger correlation id, not a resumable state handle.
Contracts
| Direction | Schema Reference | Purpose | |
|---|---|---|---|
| Input | ./references/schemas.json#/definitions/input | Pre-flight validation of push target. | |
| Output | ./references/schemas.json#/definitions/output | Push-readiness decision integrity check. |
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingcore/managed-core/skills/git-safeguard/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/linktrend/ide-development/git-safeguard)