setup-dsh-bridge

setup-dsh-bridge is a skill for Codex from HazenSun/dsh-codex-bridge. It costs 70 tokens per session (889 once invoked), scanned A, original, Apache-2.0.

A setup guide for DSH Codex Bridge, which connects model providers to named settings for running coding-agent tasks in a Git project.

In plain words
What is it for?
Use it to install or repair the Bridge, add or switch models, change the default profile, preview settings, roll back a profile change, or investigate delegation errors.
Why use it?
It helps diagnose missing or invalid Bridge settings and keeps model, project, and safety changes controlled. It also prevents credentials from being copied or exposed in chat.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit Use it to install or repair the Bridge, add or switch models, change the default profile, preview settings, roll back a profile change, or investigate delegation errors.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hazensun/dsh-codex-bridge/setup-dsh-bridge
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add HazenSun/dsh-codex-bridge --skill setup-dsh-bridge
Clone the repo
git clone --depth 1 https://github.com/HazenSun/dsh-codex-bridge

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for setup-dsh-bridge

README.md
[![agentmods](https://agentmods.dev/badge/skills/hazensun/dsh-codex-bridge/setup-dsh-bridge/github.svg)](https://agentmods.dev/skills/hazensun/dsh-codex-bridge/setup-dsh-bridge)
Your own site
<a href="https://agentmods.dev/skills/hazensun/dsh-codex-bridge/setup-dsh-bridge"><img src="https://agentmods.dev/badge/skills/hazensun/dsh-codex-bridge/setup-dsh-bridge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for setup-dsh-bridge

Your own site · 80×15
<a href="https://agentmods.dev/skills/hazensun/dsh-codex-bridge/setup-dsh-bridge"><img src="https://agentmods.dev/badge/skills/hazensun/dsh-codex-bridge/setup-dsh-bridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 889 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.00889
Opus 5 $0.00035 $0.00445
Sonnet 5 $0.00014 $0.00178
Haiku 4.5 $0.00007 $0.00089

Measured 8d ago against content hash aa1ea32e35fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

setup-dsh-bridge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/dsh-codex-bridge/skills/setup-dsh-bridge/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set up DSH Bridge

Treat setup and model routing as a controlled configuration workflow. DSH owns Provider adapters and credentials; Bridge owns named execution Profiles, project defaults, safety limits, and routing. Never request, display, copy, or write an API key, Cookie, OAuth token, private endpoint, or credential value.

Start with status

  1. Call get_setup_status before proposing a change.
  2. Follow only the returned next_actions; do not guess that the installation is ready.
  3. If the MCP server cannot start because DSH or its codex-bridge Profile is missing, run dsh-bridge setup --project . --dry-run when local shell execution is available. Ask before running the same command without --dry-run, because it changes user-level DSH or Codex state.
  4. Stop at a clear manual action when DSH needs a credential. Tell the user to configure it through DSH Settings or an approved environment-variable reference, then rerun status. Never accept the literal secret in chat.

Select an exact DSH route

Call discover_dsh_models. Select only Provider and Model IDs returned by DSH. Use the model description, modalities, reasoning levels, and the user's stated purpose to suggest a semantic Profile ID such as fast-code, deep-review, or vision-analysis; do not make the raw model name the only user-facing meaning.

If the user asks for a Provider or Model that DSH does not expose, report it as unavailable. For a new Provider protocol or custom gateway, direct the user to configure the Provider in DSH first. Read Profile management when creating or replacing a complete Profile.

Preview before every write

  1. Build the smallest ProfileChange that satisfies the request. For an existing Profile, prefer update.changes over replacing the full Profile.
  2. Call preview_profile_change; do not edit bridge.yaml with an unrestricted file tool.
  3. Show the user the semantic effect, affected Profile/project default, exact DSH route, and any restart requirement. Do not dump unrelated configuration.
  4. Apply only after the user approves the preview. Pass the preview's before_revision as expected_revision; a revision conflict requires a new preview.
  5. Call get_setup_status and list_profiles after the change. Never claim success from the write response alone.

Read the full file on GitHub · 46 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 46 lines · 70 tokens per session scan A aa1ea32e35fa

Subscribe to this mod's changes

setup-dsh-bridge is a skill published in the GitHub repository HazenSun/dsh-codex-bridge (1 stars, last pushed 5d ago), licensed Apache-2.0. It adds 70 tokens to every session and 889 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories