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 Master-1st/codex-deepseek-visible-stream --skill deepseek-visible-streamgit clone --depth 1 https://github.com/Master-1st/codex-deepseek-visible-streamWrote 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/master-1st/codex-deepseek-visible-stream/deepseek-visible-stream)<a href="https://agentmods.dev/skills/master-1st/codex-deepseek-visible-stream/deepseek-visible-stream"><img src="https://agentmods.dev/badge/skills/master-1st/codex-deepseek-visible-stream/deepseek-visible-stream/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/master-1st/codex-deepseek-visible-stream/deepseek-visible-stream"><img src="https://agentmods.dev/badge/skills/master-1st/codex-deepseek-visible-stream/deepseek-visible-stream.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 | $0.00111 | $0.01523 |
| Opus 5 | $0.00056 | $0.00762 |
| Sonnet 5 | $0.00022 | $0.00305 |
| Haiku 4.5 | $0.00011 | $0.00152 |
Grade A, and why
deepseek-visible-stream 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepSeek Codex Router
Deploy DeepSeek V4 inside Codex as a bounded specialist. Keep Sol in control of intent, permissions, planning, integration, verification, and the final answer.
Route work
- Keep ambiguous requirements, architecture decisions, cross-worker coordination, safety judgments, integration, and the user-facing conclusion with Sol.
- Route local repository inspection, tool execution, mechanical edits, and bounded verifiable work to Luna when available.
- Route routine independent checks, low-cost analysis, and latency-sensitive work to DeepSeek V4 Flash.
- Route mathematics, algorithms, architecture, complex debugging, adversarial review, and critical research to DeepSeek V4 Pro.
- Route Chinese drafting, rewriting, translation, polishing, and summarization to DeepSeek by default. Use Flash for routine text and Pro for academic, quality-first, or critical text; Sol verifies facts and performs the final integration.
- Give DeepSeek a self-contained task packet. It has no implicit access to local files, tools, or conversation history.
- Never create Luna-to-DeepSeek or DeepSeek-to-Luna recursive chains.
Install and validate
-
Confirm the host is Windows and the MCP command uses Windows PowerShell 5.1 (
powershell.exe). -
Install or upgrade with the bundled installer. The legacy Hotfix3 filename is retained for in-place upgrades:
$env:DEEPSEEK_INSTALL_NO_GUI = '1' powershell.exe -NoProfile -ExecutionPolicy Bypass -File scripts\Install-DeepSeek-Visible-Stream-Hotfix3.ps1For an interactive install, run
scripts\Install-DeepSeek-Visible-Stream-Hotfix3.cmd. -
Fully exit and restart Codex or ChatGPT. MCP servers are long-lived; replacing a file does not reload an existing process.
-
Run the no-API regressions:
powershell.exe -NoProfile -ExecutionPolicy Bypass -File scripts\Test-Utf8-Input-Regression.ps1 powershell.exe -NoProfile -ExecutionPolicy Bypass -File scripts\Test-Control-Plane-Contract.ps1
What ships with it
9 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.
- agents/openai.yaml 345 B
- scripts/Install-DeepSeek-Visible-Stream-Hotfix3.cmd 273 B runs code
- scripts/Install-DeepSeek-Visible-Stream-Hotfix3.ps1 94 KB runs code
- scripts/source/server.ps1 44 KB runs code
- scripts/source/stream-worker.ps1 16 KB runs code
- scripts/Test-Control-Plane-Contract.ps1 19 KB runs code
- scripts/Test-DeepSeek-Visible-Streaming.cmd 186 B runs code
- scripts/Test-DeepSeek-Visible-Streaming.ps1 6.4 KB runs code
- scripts/Test-Utf8-Input-Regression.ps1 4.7 KB runs code
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 · 93 lines · 111 tokens per session scan A 78997da60918
deepseek-visible-stream is a skill published in the GitHub repository Master-1st/codex-deepseek-visible-stream (2 stars, last pushed 26d ago), licensed MIT. It adds 111 tokens to every session and 1,523 once invoked, about $0.0006 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
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
image-generation
Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.
ast-grep
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for…
analyzing-powershell-script-block-logging
Parse Windows PowerShell Script Block Logs (Event ID 4104) from EVTX files to detect obfuscated commands, encoded payloads, and living-off-the-land techniques. Uses python-evtx to extract and reconstruct multi-block scripts, applies entropy analysis and pattern matching for Base64-encoded commands, Invoke-Expression…
oh-my-posh
Install, configure, or troubleshoot Oh My Posh/ohmyposh: shell init, themes, segments, Nerd Font icons, and prompt setup on PowerShell, zsh, bash, or fish.
deepcode-self-refer
Answers questions about Deep Code CLI itself — including features, configuration options, slash commands, Skills, MCP integration, permissions, notifications, session persistence, and troubleshooting. Use this when users ask how to configure or use Deep Code, how to set up an MCP server, configure notifications (such…