sbc-retrieve
Spawn a retrieval sub-agent for second-brain Q&A so search and pack stay off the parent context.
Skill by SpillwaveSolutions
Chalk Labs
Need help deploying sbc-retrieve?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/spillwavesolutions-sbc-retrieve
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/sbc-retrieve
What's inside
- Skill name
sbc-retrieve- Description
- Spawn a retrieval sub-agent for second-brain Q&A so search and pack stay off the parent context.
- License
- MIT
- Instructions
- 55 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# sbc-retrieve
Parent-facing. Read [docs/RETRIEVAL.md](../../docs/RETRIEVAL.md) first.
For Q&A, or "what does the brain say", spawn a child. Do not run
`sbc_common.py pack`, `pkc_pack`, `sac_pack`, `dekc_pack`, or
`rkc_pack` in this parent turn. Progressive disclosure still lands
the pack in the parent if you run it here.
Do not invent `rel` values. See `docs/typed-edges.md`.
## Foundation retrievers
Spawn the pack that owns the nouns. Each child returns a Retrieval
card only. Fan out in parallel when the question crosses planes.
| Plane | Spawn |
|-------|-------|
| Project memory (Feature, DecisionRecord, Meeting, Experiment) | PKC `knowledge-retriever` (`/pkc-retrieve`) |
| Architecture (Service, ApiContract, Runtime, blast radius) | SAC `architecture-retriever` (`/sac-retrieve`) |
| Data platform (Table, Metric, LineagePath, DataProduct) | DEKC `data-retriever` (`/dekc-retrieve`) |
| Research (ResearchQuestion, Finding, Claim, Evidence) | RKC `research-retriever` (`/research-retrieve`) |
Do not move those agents into core.
## Core-owned concepts
For Concept, ContextPack, TypedEdge, AgentIdentity, or WriteEvent
only, spawn a short-lived child Task (host equivalent). The child
runs:
```bash
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sbc_common.py" pack \
--bundle "${SECOND_BRAIN_ROOT:-knowledge}" \
--root "/concepts/example.md" \
--tiny --summary
```
`--tiny` is 1 hop / 8 nodes. `--summary` is compact markdown, bodies
off, fail-closed budget. The child fills the Retrieval card from
that stdout and stops.
## Job-function packs without a retriever
Same temporary path: short-lived child Task, `sbc_common.py pack --tiny --summary`,
same card. Add a pack-local retriever later if the pack needs its own
scoring.
## Consume
Keep only the card. Answer from it. If Next is `deepen` or
`try-alt-seed`, spawn again. Do not paste hit lists or pack bodies
into this context.From SpillwaveSolutions/second-brain-core, MIT.
More from SpillwaveSolutions/second-brain-core
- 0.439score
sbc-session
SpillwaveSolutions
Open or close an isolated second-brain write session (worktree + PR).
SkillBFreshness: B★ 2Claude Code +9 - 0.437score
sbc-init
SpillwaveSolutions
Scaffold the Second Brain Core catalogs in a shared second-brain bundle.
SkillBFreshness: B★ 2Claude Code +9 - 0.437score
sbc-pack
SpillwaveSolutions
Build a bounded ContextPack from a Second Brain Core root concept (default 2 hops, 20 nodes, 1/4 window token budget).
SkillBFreshness: B★ 2Claude Code +9 - 0.437score
sbc-capture
SpillwaveSolutions
Capture a Second Brain Core noun into the shared second brain via the deterministic write helper.
SkillBFreshness: B★ 2Claude Code +9 - 0.433score
sbc-doctor
SpillwaveSolutions
Health-check the Second Brain Core catalogs and report empty indexes or missing schemas.
SkillBFreshness: B★ 2Claude Code +9 - 0.430score
cursor-second-brain-core
SpillwaveSolutions
Bind a Cursor agent (including Grok Bot cloud sessions) to the second-brain-core ContentPack.
SkillBFreshness: B★ 2Claude Code +9 - 0.430score
grok-bot-second-brain-core
SpillwaveSolutions
Bind a Grok Bot agent to the second-brain-core ContentPack.
SkillBFreshness: B★ 2Claude Code +9 - 0.430score
deep-agents-second-brain-core
SpillwaveSolutions
Bind LangChain Deep Agents to second-brain-core.
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 1
- Open issues
- 1
- Last commit (this folder)
- Sep 12, 2026 (1 month ago)
- Last release
- Sep 12, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from SpillwaveSolutions
- 0.465score
pkc-doctor
SpillwaveSolutions
Run a one-screen health check on a PKC knowledge bundle — broken links, orphans, thin Features, decision conflicts, open Questions, stale…
SkillAFreshness: A★ 1Claude Code +9 - 0.465score
pkc-init
SpillwaveSolutions
Scaffold a Project Knowledge Capture OKF bundle with all PKC catalogs (meetings, experiments, discoveries, decisions, features, …), root index.md, and log.md.
SkillAFreshness: A★ 1Claude Code +9 - 0.465score
pkc-capture-prd
SpillwaveSolutions
Ingest a PRD journey section as Persona, UserJourney, JourneyStage, Scenario, and UserStory concepts, and link them to Features, Epics, and work Stories.
SkillAFreshness: A★ 1Claude Code +9 - 0.465score
pkc-capture-meeting
SpillwaveSolutions
Capture meeting notes into OKF Meeting concepts, extract DecisionRecords, and optionally create WikiTicket action items + TicketLinks.
SkillAFreshness: A★ 1Claude Code +9 - 0.465score
pkc-index
SpillwaveSolutions
Refresh, inspect, or drop the disposable SQLite/FTS5 knowledge index.
SkillAFreshness: A★ 1Claude Code +9 - 0.463score
pkc-capture-discovery
SpillwaveSolutions
Capture research, competitive scans, user findings, and discovery notes as OKF Discovery concepts with source, confidence, and informs links.
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get sbc-retrieve running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
sbc-retrieve skill. Agent Mart. https://agentmart.dev/skills/spillwavesolutions-sbc-retrieve (last updated 2026-10-24)