-
Notifications
You must be signed in to change notification settings - Fork 1
Home
slipstream is not affiliated with or endorsed by Anthropic. Claude and Claude Code are trademarks of Anthropic, referenced here only to describe compatibility.
slipstream is a Claude Code plugin. You install it into Claude Code in VS Code and it makes Claude work through precise tools instead of whole-file reads, keeps context alive across compaction, ships a guardrailed skill library for production sites on Cloudflare, Supabase, Vercel and Resend, and stands up a live local dashboard so you can watch the agents work.
It is not a CLI you run as a product. There is a small helper binary the plugin calls from its hooks, its slash commands and a bundled MCP server, but you never invoke it directly.
-
Claude works through precise tools. A bundled MCP server exposes
sp_map,sp_symbol,sp_linesandsp_search, so Claude pulls one declaration instead of opening the whole file. See MCP tools and Token efficiency. -
Memory builds itself, and you can search it. Every turn is captured as a compact observation and made semantically searchable through a three-layer search (
sp_search_memory→sp_timeline→sp_observations), so past work is recoverable without anyone writing it down. See Observation memory and semantic search. -
Context survives compaction. A
PreCompacthook writes a structured digest before Claude Code trims the conversation; the next session reloads it. See Lossless compaction. -
You watch the agents in a dashboard. Session start boots a
127.0.0.1server and prints the URL into chat; a Memory search panel queries your project's observations. See Live agent dashboard. -
You see the budget in the statusline.
cp | ctx 12% ok | mem 4 | obs 37 | skill scoped-read. See Statusline.
%%{init: {'theme':'base','themeVariables':{'primaryColor':'#0d1117','primaryTextColor':'#f5f7fa','primaryBorderColor':'#38bdf8','lineColor':'#22d3ee','fontFamily':'monospace'}}}%%
flowchart TD
subgraph CC[Claude Code in VS Code]
Hooks[Hooks incl. PreCompact]
Cmds[Slash commands]
Skills[63 agent skills]
Agents[Subagents]
SL[Statusline]
end
CC --> MCP[Bundled MCP server sp_*]
Hooks --> Helper[slipstream helper]
Cmds --> Helper
Agents --> MCP
MCP --> Map[Project map]
Helper --> Map
MCP --> Mem[Persistent memory]
Helper --> Mem
Hooks -->|PreCompact| Digest[Session digest]
Digest --> Mem
Hooks --> Log[(Event log)]
Log --> Server[Local SSE server 127.0.0.1]
Server --> UI[Live dashboard]
SL --> Budget[Context budget]
Map -->|read index, pull one slice| Tokens[Fewer tokens per read]
Mem -->|reloaded at session start| Survive[Context survives compaction]
- Dashboard /api/health. Every dashboard advertises its version, pid and boot timestamp on a tiny local-only JSON endpoint.
-
Version-aware restart.
sp_dashboardnow probes/api/health; if the running version is behind the installed build, the old process is signalled and a fresh dashboard takes the port. No more stale UIs after an upgrade. -
Stable URL file. After every start,
<project>/.claude/slipstream/dashboard.urlis written so any caller can find the live URL. -
New doctor checks.
duplicate-registrationflags slipstream wired via both the plugin and.mcp.json.double-emitflagsSLIPSTREAM_MCP_EMIT=1set on top of active hooks.stale-dashboardflags a running dashboard whose version is behind the installed package.
- More install paths. First-class guides for JetBrains, Cursor, Windsurf and Antigravity, alongside the existing VS Code plugin path.
-
Map watcher. Optional
--watch-mapmode keeps the project map in step with the working tree, so scoped reads do not return stale ranges after a rename. - Token forecast. The statusline now shows how many steps remain before the warn threshold, so compaction happens on your terms.
- Replay export. Bundle a session into a portable archive for debugging, sharing or attaching to a bug report.
-
Configurable redaction. A
.claude/slipstream/redact.jsonfile with default patterns for the obvious leakers and a clean hook for custom rules. - Drift detection. Surfaces stale maps, missing references and gauge-versus-truth disagreement as observations with a clear suppression path.
- Per-skill opt %. A breakdown of token savings by skill, so you see which parts of the workflow are pulling their weight.
-
CI mode. A
--ciflag that emits JSON-line stdout, exits non-zero on drift, and plugs into GitHub Actions with a few lines of YAML. -
Lessons. Recurring observations collapsed into durable, citable lessons surfaced through
sp_lessons.
| Page | What it covers |
|---|---|
| Install in VS Code | Marketplace add, install, first run, doctor |
| MCP tools | The bundled server and every sp_ tool |
| Observation memory and semantic search | Self-building memory, the local embedding, three-layer search, lesson distillation |
| Cross-IDE support | The dashboard, budget gauge and tools in Cursor, Windsurf, Antigravity, VS Code |
| Lossless compaction | The PreCompact digest and the reload |
| Memory recall | Signal-ranked relevant recall, not load-everything |
| Live agent dashboard | Hooks, event log, server, UI, replay |
| Statusline | The status bar line and how to enable it |
| Output style | The terse, token-lean style |
| Subagents | sp-shipper, sp-schema, sp-reviewer |
| Token efficiency | The worked before/after numbers |
| Architecture | Repo shape, modules, the data path |
| Memory system | The file-based store and the index |
| Skill engine | The skill contract and loader |
| Skill catalogue | The 63 skills by category |
| Writing a skill | Author a skill that passes validation |
| Hooks | Every wired hook and what it emits |
| Configuration and tuning | Every knob and env var |
| Data formats | Map JSON, memory frontmatter, the event log |
| Performance and benchmarks | Real numbers from this machine |
| Design decisions | Choices made and alternatives rejected |
| Security model | Local-only, redaction, what to trust |
| Testing strategy | What the 120 tests cover and why |
| Examples and recipes | Copy-paste flows |
| Comparisons | Versus the obvious alternatives |
| Integrations | Cloudflare, Supabase, Vercel, Resend |
| Contributing | Build, test, write an extension |
| FAQ | Common questions |
| Troubleshooting | Symptoms and fixes |
| Roadmap and limitations | What I will and will not add |
SarmaLinux . sarmalinux.com . Repository
Start here
Install paths
v0.6.0 features
- Map watcher
- Token forecast
- Replay export
- Configurable redaction
- Drift detection
- Per-skill opt %
- CI mode
- Lessons
Headline features
- MCP tools
- Observation memory & search
- Cross-IDE support
- Lossless compaction
- Memory recall
- Live agent dashboard
- Statusline
- Output style
- Subagents
Token efficiency
Skills
Internals
- Architecture
- Memory system
- Hooks
- Mind map and status
- Configuration and tuning
- Data formats
- Performance and benchmarks
- Design decisions
- Security model
- Testing strategy
Reference
SarmaLinux . sarmalinux.com