Smart Sourcing
Decide which factual claims in agent work need live citations versus trusted inference so research stays accurate without blowing token budgets.
Overview
Smart Sourcing is a journey-wide agent skill that chooses when tool-backed citations are worth the token cost—usable whenever a solo builder needs to verify high-value claims before committing.
Install
npx skills add https://github.com/athola/claude-night-market --skill smart-sourcingWhat is this skill?
- Require sources for version numbers, performance stats, security advice, API specs, release dates, pricing limits, and d
- Skip mandatory sourcing for stable concepts, opinion, and low-risk narrative where verification cost exceeds accuracy ga
- Frames full sourcing as roughly 10–16× more expensive and targets verification only on high-value claims
- Pairs with web search and fetch workflows via usage patterns for research, citation, and verify-claim triggers
- Full sourcing described as roughly 10–16× token increase versus selective verification
- Require-sources table covers seven high-value claim types including versions, performance, security, APIs, dates, pricin
Adoption & trust: 1 installs on skills.sh; 304 GitHub stars; 2/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You want trustworthy answers from your coding agent without paying for full web sourcing on every sentence.
Who is it for?
Agents that research libraries, compare performance, or draft security and API docs where a few wrong facts are costly.
Skip if: Workflows that must cite every sentence for compliance, or tasks with no factual claims where sourcing rules add no value.
When should I use this skill?
Use before research tasks or when deciding whether a claim needs verification; triggers include research, source, citation, verify claim, web search, and fetch.
What do I get? / Deliverables
The agent applies a fixed claim-type checklist so only version, security, API, pricing, and similar high-risk statements trigger verification while the rest stays lean.
- Per-claim sourcing decision (require source vs proceed without)
- Citations attached only for flagged claim types when tools are available
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Scout a framework release note and only fetch sources for stated version and deprecation claims.
Document an SDK endpoint and require citations for parameter lists while skipping sources for general architecture explanation.
Recommend password hashing and force verification on security recommendations while not sourcing obvious coding style opinions.
Draft pricing comparison copy and source tier limits and dates but not subjective positioning lines.
Estimate competitor performance and source quantitative benchmarks only.
How it compares
Use instead of always-on web search or never citing—it's a decision policy, not a search integration.
Common Questions / FAQ
Who is smart-sourcing for?
Solo and indie builders running Claude Code, Cursor, or Codex who do frequent research, comparisons, or factual docs and need citation discipline without maximal token spend.
When should I use smart-sourcing?
Before research tasks, when verifying a specific claim, or during Build docs, Ship security guidance, and Launch copy whenever version numbers, APIs, or pricing appear; also at Idea stage when scouting tools and competitors.
Is smart-sourcing safe to install?
It is markdown procedural guidance with no bundled tools in the skill manifest; review the Security Audits panel on this Prism page before enabling it in production agent configs.
SKILL.md
READMESKILL.md - Smart Sourcing
# 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 Type | Example | Why Source | |------------|---------|------------| | **Version numbers** | "Python 3.12 added..." | Versions change, easy to verify | | **Performance claims** | "30% faster than..." | Quantitative claims need evidence | | **Security recommendations** | "Use bcrypt for..." | Security advice must be current | | **API specifications** | "The function accepts..." | APIs change between versions | | **Release dates** | "Released in Q4 2025" | Factual, verifiable | | **Pricing/limits** | "Free tier allows 1000 requests" | Business terms change | | **Deprecated features** | "X was removed in version Y" | Breaking changes need verification | ### DO NOT Require Sources | Claim Type | Example | Why No Source | |------------|---------|---------------| | **General concepts** | "Async improves concurrency" | Foundational knowledge | | **Code examples** | Demonstrative snippets | Illustrative, not factual claims | | **Opinion/preference** | "Consider using..." | Clearly framed as suggestion | | **Common knowledge** | "Git tracks changes" | Universal understanding | | **Logical derivations** | "Therefore, X implies Y" | Reasoning, not factual claim | | **Syntax** | "Use `def` for functions" | Language documentation is stable | ## Decision Framework ``` 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 | Confidence | Action | |------------|--------| | High (stable facts) | State directly | | Medium (may have changed) | Add verification note | | Low (uncertain) | Source or acknowledge uncertainty | ## Token Cost Analysis | Approach | Token Cost | Use Case | |----------|------------|----------| | No sourcing | Baseline | General knowledge | | Uncertainty marker | +5-10 tokens | Medium confidence | | Single source | +2-5k tokens | High-value claim | | Multiple sources | +10-20k tokens | Research 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