deepseek-harness-game-studios

DeepSeek Harness Game Studios

Install · Implementation status · Project structure · Testing your customizations · Verification · License

Turn a single DeepSeek Harness session into a full game development studio. 49 agents. 76 skills. One coordinated AI team.

This is a port of Claude Code Game Studios (CCGS) to DeepSeek Harness (DSH) — not a rewrite from scratch: the skills, agents, rules and docs come from upstream (MIT); this repository provides the DSH-native runtime (Node hooks, skill generation, machine-level install, plugin bridge).

Provenance

Upstream project	Donchitos/Claude-Code-Game-Studios
Upstream version this port tracks	v1.1.2 (commit b21fa0f, 2026-09-29)
Upstream license	MIT (Copyright © 2026 Donchitos) — reused here
This repository	deepseek-harness-game-studios (DSGS) v0.1.4
Port strategy	Dual stack, one source: .claude/ is the content source (upstream text, kept verbatim); .dsh/** is generated by tools/build-dsh.mjs

Upstream targets Claude Code (.claude/, .sh hooks, bash one-liners, @path imports). None of that runs under DSH (no bash tool, piped child processes are denied by the sandbox, @path is not expanded), so instead of editing upstream content we generate a DSH-runnable equivalent and prove no content loss.

This repository is the plugin package. The framework it installs is bundled under payload/ — you never need to look at it.

Install

① GUI

Plugins → Add plugin → paste https://github.com/HYClub/deepseek-harness-game-studios → Install → restart dsh web.

② Command line

dsh plugin --profile web add https://github.com/HYClub/deepseek-harness-game-studios

Then restart dsh web.

On first load the plugin installs the framework at machine level (~/.dsh/dsgs plus user-level bootstrap skills). After that:

new working directory → new session → type /start

/start checks whether the workspace is initialised; if not it initialises it first, then walks you through onboarding.

What the plugin writes to your machine (and how to undo it)

Path	What
~/.dsh/dsgs/**	framework payload (skills, agents, rules, hooks, tools, docs, instruction files)
~/.dsh/skills/dsgs-init/SKILL.md, ~/.dsh/skills/start/SKILL.md	user-level bootstrap skills

It never touches a project directory and never overwrites project files. To undo:

Remove-Item -Recurse -Force "$env:USERPROFILE\.dsh\dsgs"
Remove-Item -Recurse -Force "$env:USERPROFILE\.dsh\skills\dsgs-init","$env:USERPROFILE\.dsh\skills\start"
# then uninstall the plugin and restart dsh web

Implementation status

✅ Implemented (all measured)

Item	Status	Notes
Skills	✅	all 74 upstream skills ported, each invocable as /name
Agent role cards	✅	49, as .dsh/agents/<name>.md + delegation conventions
Rules	✅	13, including an equivalent for upstream's path-scoped rule engine: a PostToolUse hook injects the matching rule text after each write/edit
Hooks	✅	12 upstream scripts → 14 Node rewrites, bridged via dsh-hooks-claude-code; all 9 upstream events covered
Hooks actually run	✅	mount 10/10 · protocol 12/12 · live events 6/9
Config resolution	✅	project.yaml single source; Node ports of resolve_config / __call resolve_setting
Helper scripts	✅	every upstream .sh has a Node port (.dsh/scripts/*.mjs) that runs inside the sandbox
Content fidelity	✅	258 files / 42,895 lines: 96.0% verbatim, 3.1% documented rewrites, 0.5% structural, 0.4% fuzzy, 0 unexplained loss
Machine-level install	✅	the plugin ships the payload and installs it on first load; /start initialises an empty workspace (measured: 928 items)
/statusline	✅	studio status line stage · posture · epic > story · Sprint n/m · engine (+13 unit tests)
Nested delegation	✅	subagent.maxDepth: 2 — parent → child → grandchild verified (DSH default is 1)
One-package install	✅	one package = hook bridge + status line projection + payload self-install
DSGS-only skills	✅	statusline, dsgs-install (not in upstream)

❌ Not implemented / no equivalent (with reasons and substitutes)

Item	Status	Why	Substitute
Docked status bar above the composer	❌	DSH's client roster only lists @deepseek-ai/* packages (measured: 60+ entries, ours absent even with a dsh.client declaration)	/statusline skill + node .dsh/statusline.mjs; the runtime half (turns/tokens/cache/context %) is already covered by DSH's own status bar
Pre-action reminders on PreToolUse	❌	tools/pre-execute only carries allow/deny/cancel/ask; additionalContexts is read from the final tool result; agent.inject() mid-execution has no effect	validate-commit / validate-push are also registered on PostToolUse (reminder arrives after the action); set the plugin row advisory: deny to block before the action
3 hook events cannot be triggered from a prompt	⚠️	Notification, PreCompact, PostCompact have no DSH event source	mapping implemented and unit-tested, verified at mount level only (live coverage 6/9)
Per-agent tool allowlists / agent auto-discovery	❌	DSH's subagent does not accept a per-agent tool set and has no agent registry	role cards + toolFilter / persona conventions
@path imports	❌	DSH does not expand imports	.dsh/docs/studio-rules.md (merged), read on demand
!cmd`` pre-execution lines	❌	DSH has no pre-execution	rewritten as a "prerequisite command" block the model runs itself
Byte-for-byte bash ↔ Node parity	⚠️	python3 in this machine's Git Bash is a Store placeholder	2 named SKIPs, 1 case byte-identical

Project Structure

.claude/                     # Upstream content source (MIT, kept verbatim)
  settings.json              # Hooks, permissions, safety rules
  agents/                    # 49 agent definitions
  skills/                    # 74 skills (one directory per skill)
  hooks/                     # 14 scripts — 12 event hooks + yaml-helper.sh
  rules/                     # 13 path-scoped coding standards
  statusline.sh              # Upstream status line (kept as reference)
  docs/                      # workflow catalog, 39 templates, guidance
.dsh/                        # Generated by tools/build-dsh.mjs — do not edit by hand
  agents/  skills/  rules/  hooks/  scripts/  docs/
tools/                       # Generator, verifiers, Node ports, plugin, installers
dsh-src/                     # Hand-written DSH-only overlay (merged into .dsh/)
DSGS Skill Testing Framework/  # QA for the skills and agents themselves
design/ src/ assets/ tests/ prototypes/ production/   # Your project

Testing your own customizations

DSGS is a template you are meant to edit. DSGS Skill Testing Framework/ is how you check that an edited or newly written skill still holds up — a catalog of all skills and agents, per-category quality rubrics, behavioral specs, and templates for writing specs of your own.

/skill-test static [name]     # structural linter
/skill-test category [name]   # category-specific quality rubric
/skill-test spec [name]       # behavioral spec assertions
/skill-test audit             # coverage report across skills and agents
/skill-improve [name]         # test-fix-retest loop; keeps or reverts on score change

It tests the framework, never your game — game tests live in tests/.

Verification

pwsh -File tools/verify-port.ps1        # 7 steps: generate → structure → refs → fidelity → hooks → mount → suites
node tools/check-dsh.mjs                # skills=76 agents=49 rules=13 hooks=14 errors=0 warnings=0
node tools/verify-fidelity.mjs          # unexplained 0 / no content loss (258 files, 42,895 lines)
node tools/verify-hooks-mount.mjs       # 10/10 mount cases
node tools/verify-hooks-bridge.mjs      # 12/12
node tools/verify-hooks-events.mjs      # 6/9 live + 3 mount-only

Supporting this project (and upstream)

DSGS is a port; the original work — 74 skills, 49 agents, 13 rules and all the documentation — was written by the upstream author, and their own support links live in the upstream repository. If this project saves you time, please support them first. Issues and contributions about the DSH port itself belong in this repository.

License

MIT License — see LICENSE. Upstream copyright © 2026 Donchitos; the port layer (generator, Node hooks, plugin, installers, DSGS-only skills) is released under the same license.