Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Propose External Change

ASecurity

Use when asked to change state in an external system: propose the write locally and halt at the human gate without executing. Not for remote, credential, publish, deploy, or irreversible changes.

35 stars
0 votes
0 copies
0 views
Added 9/12/2026
ai-agents

Security Analysis

A100/100

Scanned 9/12/2026

Install to Claude Code

$npx -y skills add OutlineDriven/odin-claude-plugin --skill propose-external-change --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Propose External Change?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Propose External Change
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/outlinedriven-propose-external-change-odin-claude-plugin/badge)](https://www.skillsdirectory.com/skills/outlinedriven-propose-external-change-odin-claude-plugin)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: propose-external-change
description: 'Use when asked to change state in an external system: propose the write locally and halt at the human gate without executing. Not for remote, credential, publish, deploy, or irreversible changes.'
disable-model-invocation: true
---

# Propose external change

## Contract

| Field | Bound contract |
|---|---|
| Trigger | Work must change state in an external system such as a tracker, chat workspace, or remote repository rather than local files. |
| Authority | Reversible local: writes only named local artifacts (the persisted proposal); rollback is deletion of the proposal file. No remote mutation. |
| Side effect | Uses a least-privilege read connector for discovery, emits one signed and minimized write proposal, persists it, and stops at the human gate; no direct external mutation. |
| Done | The proposal is persisted and the run halts awaiting a human decision; no external write occurred without that decision. |

## Inputs

| Input | Required | Note |
|---|---|---|
| Target system type | Yes | Tracker, chat workspace, remote repository, or named external system. |
| Desired change | Yes | The exact state change to propose. |
| Read connector or credentials | No | Used only for discovery; read-only access is sufficient. |
| Signing identity | Yes | Must be supplied explicitly; no ambient fallback. |

## Procedure

1. Validate the external system type and the proposed change. Reject if the target is a local file or an unspecified system. Done when: the system type is validated and the target is not local or unspecified.
2. Establish a least-privilege read connector to the named external system. Perform discovery only. Stop if the connector cannot connect or returns no access. Done when: a read connector is established and discovery is complete, or the run stops on connection failure.
3. Validate that a signing identity is present and unambiguous. If missing or ambiguous, halt and request the identity; do not substitute or infer one. Using the discovery output, emit one JSON proposal containing: the system, the specific change, the signing identity, and the affected scope. Done when: the signing identity is validated and one JSON proposal is emitted, or the run halts requesting identity.
4. Minimize the proposal to the smallest scoped change that satisfies the requested outcome. Reject overbroad changes. Done when: the proposal is minimized to the smallest scoped change.
5. Persist the signed, minimized proposal as a local artifact. Done when: the proposal is persisted to local storage.
6. Stop. Do not execute any write against the external system. Halt at the human gate. Done when: the run halts at the human gate with no external write executed.

## Failure and recovery
| Failure class | Behavior |
|---|---|
| Connector unavailable | Run stops; no proposal emitted; external system not modified. |
| Connector returns no access | Run stops; no proposal emitted; reports the access denial. |
| Change is overbroad or ambiguous | Run stops; no proposal emitted; requests a more specific target. |
| Signing identity missing or ambiguous | Run stops; no proposal emitted; halts and requests an explicit signing identity. |

Partial-result rule: if a proposal is written before a failure, the file is left on disk as the output artifact. No external write is rolled back because none occurred.

## Output
A signed, minimized JSON proposal persisted to local storage. The proposal names the external system, the specific change, the signing identity, and the affected scope. The run halts at the human gate. No mutation of the external system has occurred.

Attribution

OutlineDrivenOutlineDriven
View sourceMore from OutlineDriven →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →