// Create and maintain an Assumption Ledger — a persistent record of assumptions, their confidence, and validation status. Use when starting a new slice, resuming work in a new context window, or when implicit assumptions risk causing drift. Tracks requirements, architecture, and implementation assumptions.
Read and write a Petri net (SDCPN) document by Automerge URL. Use when creating, editing, or querying Petri nets — adding or removing places, transitions, arcs, color types, differential equations, and parameters.
Create or update a concept capsule — the conceptual anchor for a project or feature area. Use before writing code on a new project or feature, or when terms and boundaries feel unclear. Defines glossary, invariants, happy-path scenario, and non-goals.
Write a tracer-bullet card — a precise specification for one thin end-to-end slice of work. Use when scoping a new slice, defining what to build next, or breaking a feature into provable increments. Covers target behavior, boundary crossings, risks, and definition of done.
Create characterization tests (Golden Master) for existing code so you can refactor or replace safely. Use before refactoring, strangler-replacing, or modifying code with unclear behavior. Captures observable behavior with a minimal harness, producing tests, fixtures, and a coverage report.
Methodology triage consultant for tracer-bullet development. Use when unsure which pragma skill to run next, when starting a new project, or when the current approach feels stuck. Interviews the user, assesses state, and recommends the next pragma skill.
Turn capsule invariants and boundary crossings into executable contracts. Use after creating a concept capsule, or when invariants need to be enforced in code. Covers preconditions, postconditions, constructor validation, domain types, and contract tests.
| name | assumptions |
| description | Create and maintain an Assumption Ledger — a persistent record of assumptions, their confidence, and validation status. Use when starting a new slice, resuming work in a new context window, or when implicit assumptions risk causing drift. Tracks requirements, architecture, and implementation assumptions. |
| argument-hint | [create|update|review] [paste a card/spike verdict/slice summary or describe what changed] |
Maintain a project-wide Assumption Ledger — durable memory of what was assumed, how sure we were, and how it was proved or disproved. Supports fresh context per slice without losing epistemic continuity.
Mode + context: $ARGUMENTS
Modes:
create — initialize a new ledgerupdate — add/update assumptions from a card, spike verdict, or slice resultreview — summarize current ledger and recommend what to validate nextDefault: docs/assumptions.md. If it exists, update — don't duplicate.
Each entry MUST include:
A-### (stable identifier)Assumptions track uncertainty and confidence. They are not permanent authority. When assumptions stabilize, promote them to their canonical home:
docs/capsule.md or docs/capsule-<feature>.mddocs/roadmap.md (and/or decisions log)docs/milestone.md/pragma:contract + testsWhen promoted, keep the assumption entry for history and add a "Promoted to" reference with path/anchor.
Create docs/assumptions.md with sections: Active (Proposed), Validated, Invalidated/Obsolete, Open Questions. Seed with 3-10 initial assumptions if obvious from capsule/card.
/pragma:spike/pragma:spike for unknowns, /pragma:card+/pragma:slice for E2E-validatable assumptions, /pragma:characterize for behavior already in codedocs/assumptions.md diff summary/pragma:spike or /pragma:card)State: governance, Next: /pragma:consult (or the explicitly recommended next step), Loop: /pragma:consult (default unless user explicitly continues directly)