Agent skill

Plugin Write

by NanmiCoder in NanmiCoder/dsh-auto-mode

A skill your agent uses when creating a DeepSeek Harness plugin, choosing public names for a new external DSH plugin, validating a dsh-plugin.naming.json manifest, checking reviewed central…

MITAuto-check passedDevelopment

Install Plugin Write

skills CLI
$ npx skills add NanmiCoder/dsh-auto-mode --skill plugin-write -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NanmiCoder/dsh-auto-mode plugin-write --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NanmiCoder/dsh-auto-mode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/plugin-write .claude/skills/plugin-write && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
plugin-write
GitHub stars
165
Used in
1 other repo
Token cost
~3.3k tokens
SKILL.md length
1,469 words
Files
16 (incl. scripts, references)
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when creating a DeepSeek Harness plugin, choosing public names for a new external DSH plugin, validating a dsh-plugin.naming.json manifest, checking reviewed central…

  • Works in 6 steps: Create an in-repository package — Only… → Register an in-repository package — Only… → Create an external package — Preserve… → …
  • Creating a DeepSeek Harness plugin
  • SKILL.md covers Select the Repository Mode First, Then Classify the Plugin Form, Package Checklist and Rules While Writing, plus 1 more section
  • Runs JavaScript scripts from its folder; calls pnpm and node

What it does

Plugin Write is an agent skill from NanmiCoder/dsh-auto-mode. Use when creating a DeepSeek Harness plugin, choosing public names for a new external DSH plugin, validating a dsh-plugin.naming.json manifest, checking reviewed central registrations for known conflicts, or creating a workspace package inside the deepseek-harness repository. Covers the full workflow from repository-mode and plugin-form selection through separate offline naming validation, optional online registry lookup, and package validation. Routes tool, LLM adapter, hook, service, and configuration forms to…

Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 17 other files, including scripts and reference files (for example `references/README.md`, `references/config-plugin.md` and `references/hook-plugin.md`).

It sits in Development, covering Monorepo tooling. It works with DeepSeek. The repository describes itself as: Safe automatic permissions for DeepSeek Harness. The licence is MIT.

When your agent uses it

  • Creating a DeepSeek Harness plugin
  • Choosing public names for a new external DSH plugin
  • Validating a dsh-plugin.naming.json manifest
  • Checking reviewed central registrations for known conflicts

Example prompts

  • “/plugin-write”

Requirements

  • Node.js

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Create an in-repository package — Only in the official monorepo, create packages/// with package.json, tsconfig.json, src/index.ts, and…
  2. Register an in-repository package — Only in the official monorepo, add the package to the Host or Client aggregate exactly as required by…
  3. Create an external package — Preserve the existing package manager and build system. For a new plugin, apply the external naming policy…
  4. Choose the package topology — For a replaceable capability, split service definition, provider, and consumer into separate packages only…
  5. Write the in-repository package README — Only when required by the target monorepo, put package-specific service APIs, configuration…
  6. Validate — For a new external plugin, first run node /scripts/validate-names.mjs --manifest ./dsh-plugin.naming.json; add --strict only…

What it can do on your machine

Read from SKILL.md and the folder at commit 907d663. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 4 files in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • pnpm
    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Plugin Write loads about 3.3k tokens when it runs, and up to ~18k if it reads all its reference files. Until then it costs about 198 tokens; SKILL.md has 1,469 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~198
When it runs · the whole SKILL.md, loaded when a task matches
~3.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~18k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from NanmiCoder/dsh-auto-mode at commit 907d663, republished under its MIT licence (© NanmiCoder). 1,469 words, ~3,268 tokens.

Download SKILL.mdSave it as .claude/skills/plugin-write/SKILL.md (or your agent's skills folder). This skill also uses 15 other files; get the full folder from GitHub.
name
plugin-write
description
Use when creating a DeepSeek Harness plugin, choosing public names for a new external DSH plugin, validating a dsh-plugin.naming.json manifest, checking reviewed central registrations for known conflicts, or creating a workspace package inside the deepseek-harness repository. Covers the full workflow from repository-mode and plugin-form selection through separate offline naming validation, optional online registry lookup, and package validation. Routes tool, LLM adapter, hook, service, and configuration forms to their corresponding references while separating upstream-monorepo rules from external-package rules. For an existing plugin crossing Harness versions, use this Skill's built-in version-adaptation workflow before implementing against the exact target contract.

Write DeepSeek Harness Plugins

Create a plugin package. First classify the repository mode and plugin form, then read the matching reference files, and finally validate the published entry with the smallest set of gates that covers the change.

Select the Repository Mode First

TargetRules to apply
A package inside the official deepseek-harness monorepoUse the in-repository package, tsconfig, documentation, and root-gate rules below.
An externally installable DSH pluginPreserve that repository's package layout and scripts. Use only packages and exports published by the exact target DSH version. Do not copy private, workspace versions, root tsconfig registration, or monorepo-only README gates.
An existing plugin being adapted to a new DSH hostRead references/version-adaptation.md, build the complete version corridor, and run the seven-class touchpoint preflight. If a change is breaking and the user has not yet authorized implementation, present the migration plan and wait for confirmation. After authorization, complete the version adaptation before using this Skill's form references. Form examples must never override target source, type declarations, or release notes.

Derive Cordis, Schemastery, and DSH package names and version ranges from the manifest of the exact target version. Current examples use scoped @deepseek-ai/* identifiers. Older targets may differ and must follow their own published contracts.

For every new external plugin, read references/naming-conventions.md before choosing public identifiers. Create dsh-plugin.naming.json at the plugin repository root and run the bundled read-only validator before final package validation. Treat compatibility errors as target-contract failures and prefix warnings as community recommendations; use --strict only when the plugin adopts the collision-resistant profile. This is not an official Harness manifest or a global reservation. For an existing external plugin, report naming deviations but preserve published names unless the user explicitly authorizes a compatibility-breaking rename. Packages inside the official monorepo follow the exact target checkout instead of this external naming profile.

After the offline declaration passes, read references/registry-check.md and run the separate central lookup when public network access is available. Supply the exact target Harness version. Treat a completed no-match result only as “no reviewed match”; treat timeout, malformed data, unsupported contract, or network failure as “unknown/not checked.” Never let the online lookup modify the local manifest, automatically rename a published surface, or turn an automated discovery candidate into a reservation. A formal reservation exists only after a source-backed entry is reviewed and merged in the central registry.

Then Classify the Plugin Form

Required capabilityFormReference
Model-callable tools for reading files, running commands, or searching the WebTool pluginreferences/tool-plugin.md
A new model providerLLM adapter pluginreferences/llm-adapter-plugin.md
Request, tool, or turn interception for permissions, policy, metrics, or telemetryHook pluginreferences/hook-plugin.md
A capability consumed by other plugins through ctxService pluginreferences/service-plugin.md
User-configurable behavior supplied through cordis.ymlConfig pluginreferences/config-plugin.md

A plugin may combine forms freely, such as a configurable tool plugin or a service that also registers tools. Every included form still has to satisfy its own contract. When a requirement does not match one of the five forms above, map it to an existing extension point and write a plugin that registers there. Never modify the Agent loop directly.

GoalMechanism
Add a model-callable capabilityRegister it on ctx.tools
Add a model providerRegister an adapter on ctx.llm
Provide a different capability set for one sessionAssemble it in an Agent preset
Add Shell executionImplement and register a ctx.bash backend
Add persistent terminal executionRegister a ctx.pty backend and load dsh-tool-pty
Add human commandsRegister them on ctx.commands
Add background tasksRegister them on ctx.tasks
Add filesystem access or policyImplement a ctx.fs provider or listen for fs/* policy events
Constrain launched processesUse a ctx.sandbox backend
Intercept requests, tools, or turnsUse agent/* or tools/* events; agent/turn-stopping is the turn-stopping event
Add model-visible contextCall agent.inject()
Add UI or editor integrationDrive ctx.agents and render from session/event
Add Web-client conversation nodesRegister a ConversationNodeDefinition and keyed renderers
Add persistent session stateExtend SessionEventMap, then render and replay from the log
Fork a live sessionCall ctx.sessions.fork(source, boundary?, childSessionId?)
Scope registrations to one AgentUse that Agent's agent.ctx

Package Checklist

  1. Create an in-repository package — Only in the official monorepo, create packages/<group>/<pkg>/ with package.json, tsconfig.json, src/index.ts, and README.md. Copy packages/core/tools/package.json from the target checkout, then adjust its name, description, and dependencies. Preserve target-version invariants: private: true; the root package version; type: module; main: "lib/index.js"; types: "lib/types/index.d.ts"; both types and default in exports["."] pointing to lib; the same target Cordis range in peer and development dependencies; every DSH peer dependency mirrored in development dependencies; the target Schemastery package declared in dependencies; and the target files layout plus package-specific runtime artifacts. CLI application packages must include the built bin. Do not publish undeclared source or stale artifacts. Follow relative-import conventions from the target checkout. Prefer an existing group with the matching role. A new group is only a container, and the package must sit exactly one level below it.

  2. Register an in-repository package — Only in the official monorepo, add the package to the Host or Client aggregate exactly as required by the development guide in the target checkout. A normal package belongs to one aggregate only. Do not copy historical exceptions or file lists without checking the target version. External plugins must never modify Harness root configuration.

  3. Create an external package — Preserve the existing package manager and build system. For a new plugin, apply the external naming policy and include a validated dsh-plugin.naming.json; for an existing plugin, do not silently rename public surfaces. Keep main, types, exports, files, optional bin, packaged-composition or Profile metadata, and the packed tarball consistent. Declare every runtime dependency explicitly and mirror the DSH peer dependencies needed for compilation in development dependencies. Do not make a publishable external plugin private or give it workspace version ranges merely because an in-repository template does so.

  4. Choose the package topology — For a replaceable capability, split service definition, provider, and consumer into separate packages only when they will evolve independently. Keep a single-purpose plugin in one package.

  5. Write the in-repository package README — Only when required by the target monorepo, put package-specific service APIs, configuration, events, extension points, and design notes first. End the README with the canonical "Model Experience" ordering and "Known Limitations" section from the target checkout. Describe each direct, conditional, capped, lifecycle, or auxiliary-model surface in its own H3 with the following three H4 sections, each containing a prose paragraph. Quote stable text owned by the package. For a tool Schema surface, describe only differences not already present in the generated tool catalog. Under "KV Cache Impact," distinguish append-only growth, stable repeated prefixes, replacement of earlier request tokens, and independent model requests. Then list the package changes that invalidate reuse.

    markdown
    ## Model Experience
    
    ### Request Surface and Activation Conditions
    
    #### What the Model Sees
    
    Name the exact data-dependent field, link to the generated catalog with an anchor, or introduce the verbatim text below.
    
    ##### Place the Verbatim Field Text Here When Needed
    
    ```markdown
    Copy any stable system-prompt body or other long nongenerated literal exactly from source.
    ```
    
    #### Token Impact
    
    State whether the impact is fixed, conditional, retained, replaced, capped, or has zero direct token impact.
    
    #### KV Cache Impact
    
    Describe append-only, prefix-stable, replacement, or independent behavior, including exact conditions that may invalidate reuse.
    
    ## Known Limitations and Deferred Work
    
    - **Consumer-visible gap** — State the exact missing operation or condition, its consequence, and any maintainer constraint.
  6. Validate — For a new external plugin, first run node <plugin-write-skill>/scripts/validate-names.mjs --manifest ./dsh-plugin.naming.json; add --strict only for the collision-resistant community profile. After it passes, run node <plugin-write-skill>/scripts/query-registry.mjs --manifest ./dsh-plugin.naming.json --harness-version <exact-semver> when network access is available, and report an unavailable query as unknown rather than available. Then run the applicable validation block below, focused checks, and coverage gate required by the changed behavior.

Show full SKILL.md (297 more words)Show less

Rules While Writing

  • Treat every registration as an effect. Register through ctx helpers or ctx.effect() with a disposer, and make plugin unload clean up every event listener, tool, timer, and other resource.
  • Add new behavior at documented extension points. Do not modify agent-loop.
  • Give public service methods and typed events JSDoc with @param and @returns. Define typed events through declaration merging on the target Cordis Events interface, and document the dispatch mode with @mode.
  • Do not hard-code tunable values. Any value that may differ across deployments must be a validated Config field changeable through cordis.yml.
  • Everything the model sees must be reconstructible from the session log.
  • Fail explicitly on configuration errors. Never silently skip a missing referenced object. Validate at parser, configuration, wiring, and process boundaries instead of trusting an in-process typed caller.

Validation

For packages inside the official Harness monorepo, use current root commands from the target checkout. The names below are examples only; confirm they exist before running them:

sh
pnpm install            # Register the workspace
pnpm run doc-sync
pnpm run constraints && pnpm run typecheck && pnpm run lint
pnpm run build && pnpm run hygiene

For an external plugin, use its own install, typecheck, test, static-check, and build commands. Pack the publishable artifact, inspect its contents, and load it into an isolated Profile running the exact target DSH. For an upgrade, cold-start it and complete one message → tool → reply flow or an equivalent core flow. Report every provider, operating-system, UI, or credential boundary that remains uncovered.

Select tests from the changed surface: unit-test logic; run the repository's coverage gate; run real-API end-to-end tests when provider credentials are available and execution is authorized; use credential-free snapshots for model-, protocol-, or user-visible behavior; and use a real-composition test for user-visible plugins. A package bin entry also needs a built-artifact smoke test under native Node. Complete the minimum sufficient test set under these rules without loading another Skill.

See references/README.md for the reference index.

© NanmiCoder, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 15 other files (scripts, references) in skills/plugin-write of NanmiCoder/dsh-auto-mode.

  • SKILL.md
  • references/README.md
  • references/config-plugin.md
  • references/hook-plugin.md
  • references/llm-adapter-plugin.md
  • references/naming-conventions.md
  • references/naming-policy.v1.json
  • references/plugin-naming.schema.json
  • references/registry-check.md
  • references/service-plugin.md
  • references/tool-plugin.md
  • references/version-adaptation.md
  • scripts/query-registry.check.mjs
  • scripts/query-registry.mjs
  • scripts/validate-names.check.mjs
  • scripts/validate-names.mjs

Open the folder on GitHubat commit 907d663

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in NanmiCoder/dsh-auto-mode, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Plugin Write next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Plugin Write compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Plugin Write this skillNanmiCoder/dsh-auto-mode1651 repos~3.3kAutomated safety check: PassMIT
Evals Contextzgsm-ai/costrict4.4k1 repos~1.9kAutomated safety check: PassApache-2.0
Nx Importnrwl/nx29k5 repos~3.5kAutomated safety check: PassMIT
Nx Workspacenomcopter/react-mosaic4.8k7 repos~1.9kAutomated safety check: PassCustom licence
Electron Multi-Process ArchitectureiOfficeAI/AionUi33k1 repos~1.8kAutomated safety check: PassApache-2.0
Nx Run Tasksnomcopter/react-mosaic4.8k7 repos~613Automated safety check: PassCustom licence

Similar skills

  • Evals Context

    zgsm-ai/costrict

    Provides context about the CoStrict evals system structure in this monorepo.

    4.4k GitHub starsUsed in 1 repo~1.9k tokens
    AI & LLM EngineeringAuto-check passed
  • Nx Import

    nrwl/nx

    Import, merge, or combine repositories into an Nx workspace using nx import.

    29k GitHub starsUsed in 5 repos~3.5k tokens
    DevelopmentAuto-check passed
  • Nx Workspace

    nomcopter/react-mosaic

    Explore and understand Nx workspaces. An agent skill from nomcopter/react-mosaic.

    4.8k GitHub starsUsed in 7 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Tells the agent where new code belongs in an Electron multi-process project and which APIs each process may use, with rules for new bridges, services, agents and workers.

    33k GitHub starsUsed in 1 repo~1.8k tokens
    DevelopmentAuto-check passed
  • Nx Run Tasks

    nomcopter/react-mosaic

    Helps with running tasks in an Nx workspace. An agent skill from nomcopter/react-mosaic.

    4.8k GitHub starsUsed in 7 repos~613 tokens
    DevelopmentAuto-check passed
  • Astro Developer

    withastro/astro

    Official

    Comprehensive guide for developing in the Astro monorepo. An agent skill from withastro/astro.

    63k GitHub starsUsed in 1 repo~1.5k tokens
    DevelopmentAuto-check passed

More from NanmiCoder/dsh-auto-mode

All 10 skills in this repo
  • Dsh Upgrade Audit

    NanmiCoder/dsh-auto-mode

    Audit external compatibility between two DSH (DeepSeek Harness) versions and detect reverts, producing an upgrade-report directory; compares git tags with a source checkout, or published npm…

    165 GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed
  • Plugin Workflow

    NanmiCoder/dsh-auto-mode

    Coordinate multiple DeepSeek Harness plugin Skills across inspection, migration, runtime debugging, heavy dependencies, testing, naming, and release.

    165 GitHub starsUsed in 1 repo~3k tokens
    Auto-check passed
  • Plugin Test

    NanmiCoder/dsh-auto-mode

    A skill your agent uses when writing or reviewing tests for DeepSeek Harness plugins, external DSH plugin packages, or package changes in the deepseek-harness repository.

    165 GitHub starsUsed in 1 repo~2.9k tokens
    Auto-check passed
  • Dsh Benchmark Case

    NanmiCoder/dsh-auto-mode

    A skill your agent uses when the user hands over a dsh plugin repository (or a real migration commit / version corridor) and wants its upgrade experience extracted into one auto-graded Harbor…

    165 GitHub starsUsed in 1 repo~2.7k tokens
    Auto-check: warnings
  • Plugin Release

    NanmiCoder/dsh-auto-mode

    Package, publish, and distribute DeepSeek Harness (DSH) plugins — npm pack artifact validation, GitHub/npm/hub release-track selection, tarball overrides installs for the unpublished cohort…

    165 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check: warnings
  • Plugin Heavy Dep

    NanmiCoder/dsh-auto-mode

    A skill your agent uses when adding a heavyweight browser dependency (diagram/chart renderers like mermaid, code editors, big wasm-adjacent libs) to a lightweight DSH Web plugin that must stay…

    165 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed

Works with

Categories

Questions about Plugin Write

What does Plugin Write do?

A skill your agent uses when creating a DeepSeek Harness plugin, choosing public names for a new external DSH plugin, validating a dsh-plugin.naming.json manifest, checking reviewed central…. Plugin Write is an agent skill from NanmiCoder/dsh-auto-mode.json manifest, checking reviewed central registrations for known conflicts, or creating a workspace package inside the deepseek-harness repository.

When should I use Plugin Write?

Plugin Write fits situations like: creating a DeepSeek Harness plugin; choosing public names for a new external DSH plugin; validating a dsh-plugin.naming.json manifest; checking reviewed central registrations for known conflicts.

How do I install Plugin Write in Claude Code?

Run `npx skills add NanmiCoder/dsh-auto-mode --skill plugin-write -a claude-code`. Or copy the skill folder (skills/plugin-write in NanmiCoder/dsh-auto-mode) into .claude/skills/plugin-write in your project. Claude Code loads it when a task matches its description.

How do I install Plugin Write in Codex?

Run `npx skills add NanmiCoder/dsh-auto-mode --skill plugin-write -a codex`. Or copy the skill folder (skills/plugin-write in NanmiCoder/dsh-auto-mode) into .agents/skills/plugin-write in your project. Codex loads it when a task matches its description.

Can I use Plugin Write in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NanmiCoder/dsh-auto-mode --skill plugin-write -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/plugin-write, .gemini/skills/plugin-write, .github/skills/plugin-write and .opencode/skills/plugin-write in your project.

What does Plugin Write need to run?

Going by SKILL.md and its folder, Plugin Write needs JavaScript for the scripts in its folder and the command-line tools its instructions call (pnpm and node). Our summary lists: Node.js.

Does Plugin Write access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Plugin Write safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Plugin Write use?

Plugin Write is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Plugin Write use?

About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 15k tokens, read only when the agent opens those files.

What are the alternatives to Plugin Write?

Skills that share tags, products or a category with Plugin Write: Evals Context (zgsm-ai/costrict, 4.4k stars), Nx Import (nrwl/nx, 29k stars), Nx Workspace (nomcopter/react-mosaic, 4.8k stars) and Electron Multi-Process Architecture (iOfficeAI/AionUi, 33k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Plugin Write?

NanmiCoder (a GitHub user) maintains it in NanmiCoder/dsh-auto-mode, which has 165 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 29, 2026.

Source: NanmiCoder/dsh-auto-mode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.