continue-in-dsh

continue-in-dsh is a skill for Codex from polarskicpl/dsh-codex-migrate. It costs 48 tokens per session (248 once invoked), scanned A, original, MIT.

A handoff skill that imports the current Codex task into DeepSeek Harness, another development environment, and opens it there.

In plain words
What is it for?
Moving the active task to DeepSeek Harness when the user explicitly asks to continue there.
Why use it?
It prevents developers from having to manually recreate the current task and conversation when switching environments.

Skill for Codex

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

Good fit Moving the active task to DeepSeek Harness when the user explicitly asks to continue there.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/polarskicpl/dsh-codex-migrate/continue-in-dsh
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 polarskicpl/dsh-codex-migrate --skill continue-in-dsh
Clone the repo
git clone --depth 1 https://github.com/polarskicpl/dsh-codex-migrate

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 continue-in-dsh

README.md
[![agentmods](https://agentmods.dev/badge/skills/polarskicpl/dsh-codex-migrate/continue-in-dsh/github.svg)](https://agentmods.dev/skills/polarskicpl/dsh-codex-migrate/continue-in-dsh)
Your own site
<a href="https://agentmods.dev/skills/polarskicpl/dsh-codex-migrate/continue-in-dsh"><img src="https://agentmods.dev/badge/skills/polarskicpl/dsh-codex-migrate/continue-in-dsh/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 continue-in-dsh

Your own site · 80×15
<a href="https://agentmods.dev/skills/polarskicpl/dsh-codex-migrate/continue-in-dsh"><img src="https://agentmods.dev/badge/skills/polarskicpl/dsh-codex-migrate/continue-in-dsh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 248 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 $0.00048 $0.00248
Opus 5 $0.00024 $0.00124
Sonnet 5 $0.00010 $0.00050
Haiku 4.5 $0.00005 $0.00025

Measured 9d ago against content hash 57554189a545, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

continue-in-dsh 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 9d 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.

codex/dsh-codex-bridge/skills/continue-in-dsh/SKILL.md · 17 lines

What it actually says

Continue in DSH

When the user explicitly asks to continue the current task in DSH, call continue_in_dsh immediately.

  1. Pass the current Codex task ID as codexConversationId. Also pass the current title and workspace path when available. Never substitute another recent task ID.
  2. The tool performs a one-way structured import of the current conversation into DSH and asks the DSH client to open the imported conversation.
  3. After the tool succeeds, reply with exactly: 已同步对话到 DSH。
  4. Do not create or render an inline panel. Do not register shared state, monitor DSH, route later user messages, or keep the two conversations synchronized.
  5. If the tool reports that the DSH bridge is unavailable, tell the user to start or restart DSH with the migration plugin enabled.

Do not call this tool for ordinary discussion about DSH that is not a handoff request.

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.

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. 9d ago First seen · 17 lines · 48 tokens per session scan A 57554189a545

Subscribe to this mod's changes

continue-in-dsh is a skill published in the GitHub repository polarskicpl/dsh-codex-migrate (5 stars, last pushed 12d ago), licensed MIT. It adds 48 tokens to every session and 248 once invoked, about $0.0002 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.