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.
npx skills add HazenSun/dsh-codex-bridge --skill setup-dsh-bridgegit clone --depth 1 https://github.com/HazenSun/dsh-codex-bridgeWrote 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.
[](https://agentmods.dev/skills/hazensun/dsh-codex-bridge/setup-dsh-bridge)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- Call
get_setup_statusbefore proposing a change. - Follow only the returned
next_actions; do not guess that the installation is ready. - If the MCP server cannot start because DSH or its
codex-bridgeProfile is missing, rundsh-bridge setup --project . --dry-runwhen local shell execution is available. Ask before running the same command without--dry-run, because it changes user-level DSH or Codex state. - 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
- Build the smallest
ProfileChangethat satisfies the request. For an existing Profile, preferupdate.changesover replacing the full Profile. - Call
preview_profile_change; do not editbridge.yamlwith an unrestricted file tool. - Show the user the semantic effect, affected Profile/project default, exact DSH route, and any restart requirement. Do not dump unrelated configuration.
- Apply only after the user approves the preview. Pass the preview's
before_revisionasexpected_revision; a revision conflict requires a new preview. - Call
get_setup_statusandlist_profilesafter the change. Never claim success from the write response alone.
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.
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.
- 8d ago First seen · 46 lines · 70 tokens per session scan A aa1ea32e35fa
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.
Other skills, from other repositories
shortfilm-prompt
A five-part method for writing prompts for AI-generated videos, such as Sora or Seedance. It organizes each prompt into the subject, setting, visual style, camera movement, and timed shots with sound.
ao-workflow-runner
A workflow engine that reads YAML files and runs tasks assigned to different named roles. YAML is a text format for describing structured settings and steps.
skill
Ten native DSH tools give a text-only agent eyes. Use these structured tools directly; do not shell out to the bundled Python scripts or reproduce their implementation. Vision API credentials and model settings are managed by the plugin, so tool calls do not receive credentials.
bcs-coordination
A coordination engine for tasks that involve multiple bots, including shared context, bot discovery, routing, communication, and workflow coordination. It also describes interactive uses such as games, role-play, brainstorming, and interview practice.
bbs-relay-pickup
A coordination procedure for agents that share work on tasks through a BBS task system, where BBS is the service used to claim, run, and report task steps.
bcs-coordination
A coordination system for several software agents, meaning separate automated assistants, working together.