Decide & Architect
Decide before you build.
When engineering work is ambiguous or consequential, this bundle helps you turn mixed material into bounded decisions, architecture direction, stable seams, and shared terminology before implementation.
What this bundle gives you
- A read-only route to the smallest sufficient decision activity.
- A workshop workflow that separates accepted decisions from ADR, specification, glossary, boundary, or investigation outputs.
- A pressure test for assumptions, alternatives, reversibility, and blast radius.
- Structural opportunity scanning from friction, duplication, and hotspots.
- Seam design covering ownership, contracts, dependencies, and migration.
- Domain-language governance for canonical terms, contexts, invariants, and aliases.
How the skills fit together
Master Orchestrator can route a problem to the smallest sufficient next phase. Decision Workshop organizes mixed decision material, while Decision Pressure Test examines one consequential choice. Architecture Opportunity Scan identifies structural opportunities; Architecture Seam Design turns an approved direction into a bounded seam; Domain Language Governance keeps terminology authoritative. Select the skills that fit the task. They remain separate listings and do not run as an automatic orchestrator.
Included Skills
- Master Orchestrator — routes the work to the smallest sufficient next phase with a stop condition.
- Decision Workshop — separates mixed decision material and routes accepted results to the appropriate artifact.
- Decision Pressure Test — pressure-tests a consequential decision and its assumptions, alternatives, reversibility, and blast radius.
- Architecture Opportunity Scan — ranks structural opportunities from friction, duplication, and hotspots.
- Architecture Seam Design — defines a stable module or service seam with ownership, contracts, dependencies, and migration.
- Domain Language Governance — establishes canonical terms, contexts, invariants, and aliases.
Typical Workflows
- Ambiguous request -> Master Orchestrator -> Decision Workshop -> Decision Pressure Test -> approved architecture direction.
- Structural friction -> Architecture Opportunity Scan -> Architecture Seam Design -> bounded implementation handoff.
- Behavior-changing terminology question -> Domain Language Governance -> decision or specification output.
- Consequential choice -> Decision Workshop -> Decision Pressure Test -> recorded decision with explicit follow-up.
Who It Is For
Engineers, technical leads, architects, and teams working on ambiguous or high-consequence changes who need clearer decisions before implementation.
Why Buy the Bundle
The value is the decision path: framing, pressure-testing, structural analysis, seam definition, and language governance are available together when a single engineering question crosses several boundaries. The bundle preserves the flexibility to use only the smallest sufficient skill while giving you a coherent set of independent tools.
Boundaries
The skills do not make architecture decisions automatically, implement code, authorize releases, or replace project authority. Outputs depend on the evidence and authority available for the task. No automatic orchestration, production guarantee, or universal compatibility is implied.
Individual Ownership
An Agensi bundle contains separate independently usable skill listings. Buying this bundle does not merge them into one runtime package or one executable; each included skill remains independently owned and usable, and updates are handled by Agensi for the individual listings.
Works with any agent that signs in to Agensi, such as Claude, ChatGPT, Claude Code, Cursor and Codex CLI.
One payment, lifetime access. 6 skills unlock instantly in your library.
What's included
6 skillsRoute ambiguous engineering work to the single smallest-sufficient next phase: at most one primary specialist, verified capabilities, and an explicit stop condition.
Turn a mixed architecture discussion with requirements, terminology, and open questions into accepted decisions, then route each outcome to one authoritative home: an ADR, spec, glossary, boundary, or investigation item.
Pressure-test a consequential architecture or product decision by exposing assumptions, alternatives, reversibility, blast radius, and blocking evidence before commitment.
Read-only scan that turns change friction, duplicated policy and knowledge hotspots in a codebase into a ranked table of structural opportunities, each with its cause, LEVERAGE, RISK, EFFORT and next design step.
Design a stable module or service seam by mapping ownership, comparing boundary options, and specifying contracts, dependency direction, migration, and open risks.
Resolve terminology drift across specs, APIs, and code into context-specific canonical terms with definitions, invariants, and aliases, while keeping behavior-changing questions open for a domain decision.
See it in action
Master Orchestrator
Example session with this skill installed
Route this synthetic task using the package's route output contract: "Our checkout sometimes double-charges. Figure it out and fix it." In the example context, shell and Git are available and browser access is absent. Identify only the next bounded phase, authority, mutation level, capability assumptions, and stop condition. Do not inspect a repository, run tools, claim findings, or execute a fix.
- Read your context and instructions
- Compiled the master orchestrator
Illustrative example based on the synthetic worked example included in the package. No repository was inspected, no shell or Git command was run, and no checkout finding is asserted for this listing.
MODE: FIX
PRIMARY: root-cause-debugging
VALIDATOR: none yet (no diff exists to review)
AUTHORITY: repo read; no deploy.
MUTATION LEVEL: read-only until cause is established.
CAPABILITY ASSUMPTIONS: shell and Git are available in this example; browser is absent, so any rendered check is UNVERIFIED.
WHY: The sample prompt reports incorrect behavior but supplies no established cause or reproduction; diagnosis precedes editing. Double charging makes idempotency or retry behavior a hypothesis to investigate, not a proven cause.
STOP CONDITION: Stop after a causal hypothesis has a red-capable reproduction; then route the fix to bounded-implementation and review to change-assurance-review after a concrete diff exists.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads these skills and uses them on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every skill in this bundle goes through our trust checks.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.