dsh-claude-compat

DeepSeek Harness plugin that bridges Claude Code's .claude/ directory into DSH natively — reuse your skills, slash commands, and rules with zero migration.

What it does

`.claude/` path	Mechanism	Behavior
`skills/**/SKILL.md`	DSH skill provider	Name + description in the model-visible catalog; body loads on demand via the `skill` tool. New skills appear on the next catalog reconcile — no restart.
`commands/*.md`	DSH skill provider	Same, plus user-invocable: `/command-name` works in the slash menu.
`rules/*.md`	Message-stream injection	Rules are concatenated, wrapped in a `<system-reminder>` envelope, and prepended as a user-role message at the front of the message array once per session — the same channel Claude Code uses (`prependUserContext`), which models follow reliably.

The same three directories are also read from the user-level ~/.claude/ (skills, commands, rules). Same-name skills/commands/rules are deduped with a fixed priority:

project .claude > DSH native > ~/.claude

Project entries carry rank 50, ~/.claude entries rank 700, and DSH's own bundled skills sit at rank 600 (BUNDLED_SKILL_RANK) — so a project skill always overrides the DSH-bundled and user copies, and a user skill never overrides a DSH-native one.
Rule files with the same basename in ~/.claude/rules are skipped when the project already provides one.

CLAUDE.md / AGENTS.md are not touched — DSH's built-in dsh-agent-instructions already handles those.

Requirements

DSH with a profile (e.g. web)
A project using Claude Code conventions: .claude/skills/, .claude/commands/, .claude/rules/ (all optional; ~/.claude/ equivalents are also picked up)

Install

One command — the package declares dsh.bundle, so DSH activates it automatically (no manual cordis.patch.yml editing):

dsh plugin --profile web add dsh-claude-compat

Or from GitHub:

dsh plugin --profile web add github:biedongbin/dsh-claude-compat

Restart DSH (dsh web). Done — skills show up in /, rules are injected into every new session.

Configuration

Option	Default	Description
`enableSkills`	`true`	Register the `.claude/skills` + `.claude/commands` provider (project and `~/.claude`)
`enableRules`	`true`	Inject project + `~/.claude` `rules/*.md` into the message stream
`rulesMaxBytes`	`65536`	Hard cap on total injected project rules text
`userRulesMaxBytes`	`65536`	Hard cap on total injected `~/.claude/rules` text
`projectRootMarkers`	`[".git"]`	Ancestor markers for project-root discovery
`skillRank`	`50`	Provider rank for project `.claude` skills (wins every DSH-native collision)
`skillSource`	`project-claude`	Source tag for project catalog entries
`userSkillRank`	`700`	Provider rank for `~/.claude` skills (loses to DSH-native `600`)
`userSkillSource`	`user-claude`	Source tag for `~/.claude` catalog entries
`userClaudeDir`	`~/.claude`	User-level `.claude` directory (`~` expands to the home dir)

Notes

Skill naming: DSH requires kebab-case skill names. Nested skill directories are flattened (gitnexus/gitnexus-guide → gitnexus-gitnexus-guide); invalid frontmatter names fall back to the directory name.
Rules granularity: rules are read per new session (cached per session cwd). Editing a rule mid-session takes effect in the next session.
Rules content: rules are injected verbatim as instructions to the model. Only commit rules you want the model to follow — same trust level as CLAUDE.md.

Acknowledgments

Linux.do — community
Claude Code — the .claude/ conventions this plugin bridges
DeepSeek Harness — the runtime this plugin extends

License

MIT

⭐ Star History

If this project helps you, please give it a ⭐ — it motivates us to keep improving.