Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/jsagir/mindrian-os-plugin/llms.txt

Use this file to discover all available pages before exploring further.

When you need to manage grants as a live pipeline rather than a list, /mos:opportunities surfaces the Opportunity Bank with HSI scores and decision states. Funding deserves the same rigor as product. The command does not search for grants by category — it reads your room’s specific domain, geography, venture stage, and problem definition, then generates search queries from that context. Every room gets different results.

Usage

/mos:opportunities scan
/mos:opportunities list [--domain <name>] [--knight <position>] [--min-confidence <N>]
/mos:opportunities add
SubcommandDescription
scanContext-driven grant discovery — reads your room and searches Grants.gov and Simpler Grants
listBrowse all banked opportunities ordered by HSI score, with optional filters
addManually add an opportunity to the bank

How Opportunities Enter the Bank

Opportunities enter through two distinct paths:

Grant discovery (scan)

External funding opportunities from Grants.gov and Simpler Grants, surfaced after you confirm. Nothing files automatically — you review results and decide.

Intelligence cascade (automatic)

Every methodology command that triggers analyze-room extracts gaps, convergences, and contradictions as bankable opportunities. These are filed automatically with no user action needed.
Every opportunity carries a Knight position (risk / uncertainty / mixed) and a confidence score:
  • Risk — a known problem with quantifiable odds
  • Uncertainty — an unknown problem requiring exploration
  • Mixed — a contradiction that could go either way

What Happens: scan

1

Room context read

Larry reads your room’s STATE.md (domain, geography, venture stage) and problem-definition/ content to understand your specific venture context.
2

Query generation from room data

Search queries are generated from YOUR room data — domain_keywords become API keyword parameters, geography becomes eligibility filters, venture_stage drives grant type matching (e.g. SBIR for pre-revenue). Not hardcoded searches.
3

Concurrent API search

Larry searches Grants.gov and Simpler Grants APIs concurrently, deduplicates results, and scores each by relevance to your room.
4

Results presented with HSI scores

Opportunities are surfaced in a table showing funder, program, amount, deadline, and relevance score. Larry explains the reasoning for each match.
5

Confirm-first filing decision

Larry presents the results and asks: file all, review individually, or skip. Nothing is filed without your decision.
If your room lacks sufficient context for grant discovery — no domain_keywords in STATE.md, sparse problem-definition/ content, or no geography — Larry will explain exactly what’s missing and point you to /mos:room update.

What Happens: list

The list subcommand shows all banked opportunities in a unified table covering both grant-scanned and cascade-extracted opportunities:
#SourceProgram / ProblemKnight PositionConfidenceDeadlineStatus
1NIHSBIR Phase Irisk0.852026-06-01filed
2diagnoseMissing structural coverage in market-analysisuncertainty0.80banked

Filter Flags

/mos:opportunities list --domain market-analysis
/mos:opportunities list --knight uncertainty
/mos:opportunities list --min-confidence 0.7
/mos:opportunities list --domain healthcare --knight uncertainty --min-confidence 0.5
FlagDescription
--domain <name>Filter by domain (partial match, case-insensitive)
--knight <position>Filter by Knight position: risk, uncertainty, or mixed
--min-confidence <N>Filter by minimum confidence score (0.0–1.0)

Rejection Handling

When you reject an opportunity, capturing the reason matters. Rejection is data — the reason is recorded in opportunity-bank/STATE.md and informs future scans, making them progressively smarter. Larry will ask: “Why are you passing on this one? This helps me find better matches next time.”
After a scan surfaces a candidate you want to evaluate more deeply, use /mos:qualify-opportunity to run the full Q1–Q8 qualification card. One explicit Explore after approval turns the opportunity into cited deep research filed in your opportunity bank.

Discovery is Context-Driven

The key distinction: Larry does not search for “AI grants” because a category is hardcoded. Larry searches for grants that match this room’s specific problem domain, geography, team profile, and venture stage. The room context generates the search queries:
Room dataHow it drives discovery
domain_keywords in STATE.mdAPI keyword parameters and funding categories
geography in STATE.mdEligibility filters
venture_stage in STATE.mdGrant type matching (SBIR for pre-revenue, etc.)
problem-definition/ contentAdditional domain terms

Examples

# Discover grants matching your room context
/mos:opportunities scan

# Browse all banked opportunities
/mos:opportunities list

# Filter to high-confidence uncertainty-type opportunities in healthcare
/mos:opportunities list --domain healthcare --knight uncertainty --min-confidence 0.7

/mos:qualify-opportunity

Run the full Q1–Q8 qualification card on a surfaced candidate before filing it.

/mos:research

Pull fresh web evidence that informs grant relevance and opportunity context.

/mos:graph

Query the opportunity graph to surface gaps, contradictions, and connections across the bank.

/mos:find-connections

Discover non-obvious cross-domain patterns that could reveal new funding angles.

Build docs developers (and LLMs) love