A guide for coordinating limited, evidence-based work between Claude and Codex, two coding-agent systems. It defines separate rules for asking for advice and for delegating explicitly authorized implementation work.

Sending a bounded read-only consultation or an explicitly authorized implementation task to another agent. It helps prepare task details while excluding credentials, private data, and unrelated project content.

It prevents a message between agents from being mistaken for permission to edit files, deploy, disclose information, or take other consequential actions. It also keeps the scope, authority, and acceptance checks clear.

dwi-bridge — Skill for Codex by thienhoc

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 thienhoc/dwi-by-thienhoc --skill dwi-bridge

Clone the repo

git clone --depth 1 https://github.com/thienhoc/dwi-by-thienhoc

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/thienhoc/dwi-by-thienhoc/dwi-bridge/github.svg)](https://agentmods.dev/skills/thienhoc/dwi-by-thienhoc/dwi-bridge)

Your own site

<a href="https://agentmods.dev/skills/thienhoc/dwi-by-thienhoc/dwi-bridge"><img src="https://agentmods.dev/badge/skills/thienhoc/dwi-by-thienhoc/dwi-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/thienhoc/dwi-by-thienhoc/dwi-bridge"><img src="https://agentmods.dev/badge/skills/thienhoc/dwi-by-thienhoc/dwi-bridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 538 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.

Model	Per session	Once invoked
Fable 5.1	$0.00055	$0.00538
Opus 5	$0.00028	$0.00269
Sonnet 5	$0.00011	$0.00108
Haiku 4.5	$0.00006	$0.00054

Measured 11d ago against content hash e66e37f2ed89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dwi-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 11d 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.

modules/dwi-bridge/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dwi Bridge

Coordinate native Claude and Codex capabilities while keeping human authority and evidence intact.

Boundary

Use the first-party harness or an already approved local bridge. Do not create a daemon, relay service, credential broker, or hidden transcript store merely to connect agents.

A bridge message carries information. It never grants permission to edit, push, deploy, delete, disclose data, spend money, or change visibility.

Choose the lane

Read-only consultation

Use when an independent risk review, critique, or evidence check could change the plan. Send one bounded question and the minimum relevant context. The primary agent remains responsible for every claim and action.

Execution delegation

Use only when the person explicitly authorized the other harness to implement or an approved plan assigns that step. The delegated harness becomes the sole writer for the exact scope during the call.

Task packet

Include only:

Physical working directory:
Bounded objective:
Write or effect scope:
Non-goals:
Acceptance checks:
Authority for material effects:

Exclude credentials, tokens, private keys, personal data, unrelated private content, and full transcripts when a focused excerpt is sufficient.

Coordination protocol

Confirm the physical workspace.
Select read-only advice or authorized execution.
Define one bounded outcome.
Prevent overlapping writers.
Disable recursive delegation unless the person explicitly designed it.
Treat timeout, empty output, transport failure, refusal, or failed attestation as unavailable.
Inspect live effects independently before acceptance.
Preserve failures as failures.

Authority matrix

Effect	Minimum authority
Read files in approved scope	Task or repository authority
Edit approved files	Explicit write scope
Commit or push	Explicit repository action
Deploy or change visibility	Explicit external-effect action
Share private content	Specific disclosure authority

Read the full file on GitHub · 78 lines

Files

What ships with it

1 file 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.

agents/openai.yaml 282 B

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.

11d ago First seen · 78 lines · 55 tokens per session scan A e66e37f2ed89

Subscribe to this mod's changes

dwi-bridge is a skill published in the GitHub repository thienhoc/dwi-by-thienhoc (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 538 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.

Building agents Claude Code agent-skills agentic-workflows ai-agents codex coding-agents

awsl

Run Claude Code JavaScript Workflows through the awsl compatibility runtime. Use when an agent's current task or loaded Skill requires dispatching a Claude Code Workflow but the host cannot execute that Workflow natively, or when awsl workflow inspection, durable run state, resume, or provider diagnostics are needed.

XhinLiang/awsl · 63 tokens

dwi-bridge