Atlas / Skills / composiohq / Agent Deep Links

Agent Deep LinksSAFE

skills/composiohq/agent-deep-links

A curated list of practical Codex skills for automating workflows across the Codex CLI and API.

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
—
Hosts
3 documented
License
—
Stars
16,969
01

Overview

A curated list of practical Codex skills for automating workflows across the Codex CLI and API.

Read from source at commit f10a5237c0bdOBSERVED · 2026-10-20
Advertisement
02

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
claude-desktopmentioned
codexmentioned
cursormentioned
03

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: agent-deep-links
description: Build, validate, and troubleshoot deep links for Codex, Cursor, VS Code, Visual Studio, and similar tools. Use when users ask for clickable links (especially in Slack) that open threads, files, folders, or app settings.
---

# Agent Deep Links

## Overview

Use this skill when a user asks for clickable links that should open directly in an app (usually from Slack). This includes verifying whether a target app supports deep links at all, selecting the right URL shape, and providing fallbacks when deep links are unsupported.

## Workflow

1. Identify target app + target object:
   - Thread/conversation
   - File/folder
   - Settings/new window
2. Read `references/deep-link-matrix.md` for known-good link formats and support level.
3. If support is unknown, verify locally before sending:
   - Check URL schemes in the app bundle:
     ```bash
     /usr/libexec/PlistBuddy -c 'Print :CFBundleURLTypes' /Applications/<App>.app/Contents/Info.plist
     ```
   - Smoke test launch behavior:
     ```bash
     open '<scheme>://...'
     ```
4. Construct Slack-safe link syntax:
   - `<url|label>`
5. If unsupported or uncertain, send a fallback:
   - Plain path + command
   - Documented CLI open command
   - Statement that no official deep-link format is known

## Output Rules

- Prefer absolute paths for file/folder links.
- Keep labels short and action-oriented (`Open in Cursor`, `Open in Codex`).
- Do not claim deep-link support unless it is in the matrix or just verified.
- For uncertain app routes, clearly mark as inferred/experimental.

## Common Templates

- Codex thread:
  - `<codex://threads/<thread-uuid>|Open in Codex>`
- Cursor file:
  - `<cursor://file/<absolute-path>:<line>:<column>|Open in Cursor>`
- VS Code file:
  - `<vscode://file/<absolute-path>:<line>:<column>|Open in VS Code>`
- VS Code Insiders file:
  - `<vscode-insiders://file/<absolute-path>:<line>:<column>|Open in VS Code Insiders>`

Use `references/deep-link-matrix.md` for the full cross-app matrix and support notes.
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

Audited 2026-10-20 · audit v0.4.1 · source sha f10a5237c0bdfull audit observations/trust-audit/skill/composiohq__agent-deep-links.json · Report an issue / request a re-scan
05

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-20f10a5237c0bdSAFEB89first audit
06

Questions

What does the agent-deep-links — composiohq/awesome-codex-skills skill do?

A curated list of practical Codex skills for automating workflows across the Codex CLI and API.

Is agent-deep-links — composiohq/awesome-codex-skills safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can agent-deep-links — composiohq/awesome-codex-skills access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

Which assistants does agent-deep-links — composiohq/awesome-codex-skills work with?

Its documentation mentions claude-desktop, codex and cursor. That is what the text claims, not a compatibility test we ran.

How current is this page?

The grade is for one exact copy of the source (f10a5237c0bd), read on 2026-10-20. The repository is watched, and a new audit runs when it changes — this is the first audit.

Add this badge to your README

Shows this page's audit result and links back to it. It updates when the audit does.

ModelsAtlas audit badge

Markdown
[![ModelsAtlas audit: Agent Deep Links](https://modelsatlas.com/skills/composiohq/agent-deep-links/badge.svg)](https://modelsatlas.com/skills/composiohq/agent-deep-links/)

Not your listing, or something out of date? Claim or update your listing.

Advertisement