// 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.
| name | card |
| description | 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. |
| argument-hint | [behavior to deliver in this slice] |
Write a tracer-bullet card — a precise specification for one slice of work that will be implemented with /pragma:slice.
The behavior to deliver: $ARGUMENTS
Precondition: a concept capsule must exist. If none exists, stop and recommend /pragma:capsule first. Read the capsule — the card must use glossary terms and respect invariants.
Write a card with exactly these four fields:
What should be true when this slice is done? Single declarative sentence.
Good: "A markdown file with YAML front-matter is parsed into a Post with title, date, and body." Bad: "Implement the parsing system" (too vague) / "Add support for markdown, YAML, TOML, and JSON" (too many things)
Every boundary the tracer bullet passes through:
→ [entry point] (e.g., CLI argument, HTTP request, function call)
→ [layer/boundary] (e.g., parser, domain core, adapter)
→ [exit point] (e.g., file written, response sent, value returned)
Be specific ("the PostgreSQL adapter", not "the backend"). Note boundaries that don't exist yet.
- RISK: [what might not work] → MITIGATION: [how we'll handle it]
- ASSUMPTION: [what we're assuming] → VALIDATED BY: [how we'll know]
- BUY-OR-BUILD: [buy|build + why package/tool fit is or is not acceptable]
- PROTOTYPE PLAN: [if requirement behavior is unclear, how we'll prototype and observe it]
- OUT OF SCOPE: [explicitly excluded for this slice]
/pragma:spike first, not a /pragma:slice✓ [test name] — [observable assertion checked by that test]
✓ [test name] — [observable assertion checked by that test]
/pragma:slice (red step)Cards are ephemeral — consumed by /pragma:slice, then the definition of done becomes the test.
docs/cards/ if the user wants to track themAppend to the response:
planning/pragma:slice/pragma:consult (default unless user explicitly continues directly)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 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.
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.
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.