deepseek-harness

deepseek-harness is a skill for Claude Code, Codex from ItIsMixian/Orrery. It costs 0 tokens per session (459 once invoked), scanned A, original, MIT.

A thin adapter that connects a DeepSeek harness skill to the separately installed project-orrery command-line tool. It does not include Orrery’s templates, rules, schemas, or project information.

In plain words
What is it for?
Use it to validate the Orrery dependency, route a repository worktree, attach a session when required, and follow the returned permission or continuation instructions.
Why use it?
It ensures the required external tool and repository worktree session are checked before work begins, instead of silently using missing or copied project data.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it to validate the Orrery dependency, route a repository worktree, attach a session when required, and follow the returned permission or continuation instructions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/itismixian/orrery/deepseek-harness
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 ItIsMixian/Orrery --skill deepseek-harness
Clone the repo
git clone --depth 1 https://github.com/ItIsMixian/Orrery

Made for: Claude Code, 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 deepseek-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/itismixian/orrery/deepseek-harness/github.svg)](https://agentmods.dev/skills/itismixian/orrery/deepseek-harness)
Your own site
<a href="https://agentmods.dev/skills/itismixian/orrery/deepseek-harness"><img src="https://agentmods.dev/badge/skills/itismixian/orrery/deepseek-harness/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 deepseek-harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/itismixian/orrery/deepseek-harness"><img src="https://agentmods.dev/badge/skills/itismixian/orrery/deepseek-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 459 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00000 $0.00459
Opus 5 $0.00000 $0.00230
Sonnet 5 $0.00000 $0.00092
Haiku 4.5 $0.00000 $0.00046

Measured 10d ago against content hash 41f260ea8235, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

deepseek-harness 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (index.js, scripts/check_cli_dependency.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

adapters/deepseek-harness/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orrery DeepSeek Harness Adapter

This is a thin packaged Skill. It requires the separately installed project-orrery CLI declared in adapter-manifest.json; it does not contain Orrery templates, schema, compatibility rules, or project facts.

Route the task

  1. Read the target repository's root AGENTS.md and follow its local reading order and safety boundaries before touching project files.
  2. Resolve scripts/check_cli_dependency.py against this Skill's resource base and run it with python -X utf8. If it exits nonzero, report its structured dependency error instead of falling back to copied templates or inferred rules.
  3. Before the first product write, run project-orrery worktree route --target <repo> --adapter-manifest <skill-resource-base>/adapter-manifest.json --platform-session-id <current-session-id> --json. If the runtime does not expose its session ID, stop with the returned continuation brief. When the route requires attach, run the corresponding worktree session attach command and rerun the route. Continue only when the route returns allow; never bypass dirty-primary recovery or silently rebind an existing session.
  4. Use the CLI command that matches the request:
    • project-orrery scaffold --target <repo> --title <title> --dry-run
    • project-orrery validate --target <repo>
    • project-orrery check-update --target <repo>
  5. Keep profile Plugin installation separate from target-project scaffolding, Observatory tool upgrades, and authored-document migration.
  6. Never claim that an accepted decision is implemented, that an installed scaffold is integrated, or that Agent self-report proves files were read.

For established repositories, inspect existing documentation roles and review the dry-run before any mutation. Never silently overwrite authored documents. Only use --upgrade-tools when the user explicitly requests managed Observatory updates and has reviewed the planned backups.

After implementation or validation work, update the authority layers required by the target repository's own AGENTS.md. Do not create a parallel state summary in DeepSeek-specific files.

Read the full file on GitHub · 39 lines

Files

What ships with it

6 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. 10d ago First seen · 39 lines · 0 tokens per session scan A 41f260ea8235

Subscribe to this mod's changes

deepseek-harness is a skill published in the GitHub repository ItIsMixian/Orrery (45 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 459 tokens. 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens