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

Gate Proposed Change

ASecurity

Use when asked to evaluate a proposed commit, merge, or auto-merge against a gate config. Not for landing PRs: use gate-and-merge. Read-only.

35 stars
0 votes
0 copies
1 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 gate-proposed-change --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Gate Proposed Change?

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

Security grade badge for Gate Proposed Change
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/outlinedriven-gate-proposed-change-odin-claude-plugin/badge)](https://www.skillsdirectory.com/skills/outlinedriven-gate-proposed-change-odin-claude-plugin)

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

Download Zip
Files
SKILL.md
---
name: gate-proposed-change
description: 'Use when asked to evaluate a proposed commit, merge, or auto-merge against a gate config. Not for landing PRs: use gate-and-merge. Read-only.'
---

# Gate proposed change

## Contract

| Field | Bound contract |
|---|---|
| Trigger | A proposed commit, merge, or auto-merge must clear a machine boundary before it can land. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. The gate evaluates policy and returns a verdict; it never merges, commits, pushes, or writes. |
| Side effect | Chat output only: an allow or deny verdict with the matched paths and the trigger. The gate itself performs no merge. |
| Done | Denylist is evaluated before file count before allowlist with dot-aware matching under strict version-1 config validation, and a denied change names the exact matched paths. |

## Not for

- Landing PRs: use gate-and-merge.
- Merging, committing, or pushing, this gate evaluates policy and returns a verdict only.
- Source or remote mutation: this skill is read-only.

## Inputs

- `gate config`: a YAML file with `version: 1`, a required `denylist` array of glob strings, an optional `maxFiles` number, and an optional `autoMergeAllowlist` array of glob strings. Must be supplied.
- `action`: one of `commit`, `merge`, `auto-merge`. Must be supplied; any other value is invalid.
- `paths`: the list of changed file paths in the proposed change. Must be supplied.

## Procedure

1. Validate the action is one of `commit`, `merge`, `auto-merge`. Stop with an invalid-action error on any other value. Done when: the action is validated or an invalid-action error is returned.
2. Load and strictly validate the gate config:
   - Parse the YAML.
   - Require `version` to equal `1`; otherwise reject.
   - Require `denylist` to be an array of strings; otherwise reject.
   - If `maxFiles` is present, require it to be a finite number; otherwise reject.
   - If `autoMergeAllowlist` is present, require it to be an array of strings; otherwise reject.
   - Stop with a config-validation error on any failure; do not evaluate.
   Done when: the config is validated or a config-validation error is returned.
3. Evaluate the changed paths in this exact order, returning on the first hit:
   - **Denylist first.** For each path, test it against every `denylist` glob with dot-aware matching (a `*` segment matches names beginning with `.`). If one or more paths match, deny with trigger `denylist`, listing the exact matched paths.
   - **File count.** If `maxFiles` is set and the number of paths exceeds it, deny with trigger `file-count`, listing all paths.
   - **Auto-merge allowlist.** Only when action is `auto-merge`: for each path, require it to match at least one `autoMergeAllowlist` glob with dot-aware matching. If any path matches none, deny with trigger `not-allowlisted`, listing the exact non-matching paths.
   Done when: the first matching condition returns a deny, or all conditions pass.
4. If no condition denied, allow with trigger `ok`. Done when: an allow or deny verdict is returned.

## Failure and recovery

- Invalid action: stop; return the invalid value and the accepted set. No evaluation runs.
- Config not found or unparseable YAML: stop; return the file and parse error. No evaluation runs.
- **Config schema invalid** (wrong version, non-string-array denylist, non-number `maxFiles`, non-string-array `autoMergeAllowlist`): stop; return the field and the constraint. No evaluation runs.
- Empty paths list: no denylist hit, `0 <= maxFiles`, and zero paths trivially satisfy the allowlist; result is allow with trigger `ok`. Do not invent paths.
- Partial-result rule: evaluation is all-or-nothing per condition; a deny on an earlier condition short-circuits all later conditions. The gate never mutates state, so there is no rollback; a failed validation leaves nothing to undo.
- The blocked/non-converged result is a deny verdict or a validation error, never a silent allow.

## Output

A verdict record: `allowed` (boolean), `trigger` (one of `ok`, `denylist`, `file-count`, `not-allowlisted`), `reason` (human-readable), and `matchedPaths` (the exact paths responsible; empty when `ok`); the gate emits this record only; it performs no merge, commit, or write.

Attribution

OutlineDrivenOutlineDriven
View sourceMore from OutlineDriven →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 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 →