Night Market Skill — ported from claude-night-market/conserve. For the full experience with agents, hooks, and commands, install the Claude Code plugin.

Smart Sourcing#

Intelligent sourcing that requires citations only when the cost is justified by the value of verification.

Philosophy#

Full sourcing is prohibitively expensive (10-16x token increase). Smart sourcing targets high-value claims where verification materially improves accuracy.

When to Source#

REQUIRE Sources#

Claim TypeExampleWhy SourceVersion numbers"Python 3.12 added..."Versions change, easy to verifyPerformance claims"30% faster than..."Quantitative claims need evidenceSecurity recommendations"Use bcrypt for..."Security advice must be currentAPI specifications"The function accepts..."APIs change between versionsRelease dates"Released in Q4 2025"Factual, verifiablePricing/limits"Free tier allows 1000 requests"Business terms changeDeprecated features"X was removed in version Y"Breaking changes need verification

DO NOT Require Sources#

Claim TypeExampleWhy No SourceGeneral concepts"Async improves concurrency"Foundational knowledgeCode examplesDemonstrative snippetsIllustrative, not factual claimsOpinion/preference"Consider using..."Clearly framed as suggestionCommon knowledge"Git tracks changes"Universal understandingLogical derivations"Therefore, X implies Y"Reasoning, not factual claimSyntax"Use def for functions"Language documentation is stable

Decision Framework#

text

Is this a factual claim?
├── No → No source needed
└── Yes → Would being wrong cause harm?
    ├── No (minor inconvenience) → No source needed
    └── Yes → Is verification cost-effective?
        ├── No (>5k tokens for low-value claim) → State uncertainty
        └── Yes → Perform web search, cite source

Implementation#

Inline Citations#

When sourcing is warranted:

markdown

Python 3.12 introduced `type` statement for type aliases[1].

Sources:
1. [PEP 695](https://peps.python.org/pep-0695/)

Uncertainty Markers#

When sourcing isn't cost-effective but uncertainty exists:

markdown

Python 3.12 introduced the `type` statement (verify in release notes for your version).

Confidence Levels#

ConfidenceActionHigh (stable facts)State directlyMedium (may have changed)Add verification noteLow (uncertain)Source or acknowledge uncertainty

Token Cost Analysis#

ApproachToken CostUse CaseNo sourcingBaselineGeneral knowledgeUncertainty marker+5-10 tokensMedium confidenceSingle source+2-5k tokensHigh-value claimMultiple sources+10-20k tokensResearch tasks

Examples#

Good: Source Version-Specific Claim#

markdown

User: What's new in FastAPI 0.109?

Response: FastAPI 0.109 added Pydantic v2 support as default[1] and
improved OpenAPI schema generation[2].

Sources:
1. [FastAPI Release Notes](https://fastapi.tiangolo.com/release-notes/)
2. [GitHub Release 0.109.0](https://github.com/tiangolo/fastapi/releases/tag/0.109.0)

Good: No Source for General Concept#

markdown

User: How does async/await work?

Response: Async/await enables non-blocking I/O by allowing coroutines
to yield control while waiting for operations. The event loop manages
execution, resuming coroutines when their awaited operations complete.

Good: Uncertainty Marker#

markdown

The connection pool default is typically 10 connections (verify in your
database driver documentation as this varies by library and version).

Integration#

Works with:

• conserve:response-compression - Keeps sourced responses concise
• conserve:token-conservation - Weighs source cost vs value
• memory-palace:research - Full sourcing for knowledge corpus

When To Use Full Sourcing#

When NOT To Use#

• Internal project code that doesn't need citations
• Casual conversation without factual claims

Escalate to full sourcing (accept high token cost) for:

• Knowledge corpus entries (permanent documentation)
• Security advisories (safety-critical)
• Compliance/legal claims (audit requirements)
• Research tasks (user expects thorough investigation)

For these cases, use memory-palace:research workflow which is designed for comprehensive sourcing.