Closing the intent-to-code chasm - specification-driven development with BDD verification chain
86
92%
Does it follow best practices?
Impact
86%
1.82xAverage score across 14 eval scenarios
Advisory
Suggest reviewing before use
The payments team at an e-commerce platform has discovered a bug in their checkout flow. When a payment fails due to a temporary network issue, the retry mechanism sometimes charges customers twice. This has been reported by 3 customers in the past week and the support team has confirmed the root cause points to the payment state machine not checking for existing pending charges before submitting a new one.
The team needs a formal bug record created and the appropriate fix tasks added to their existing tasks.md file, so the engineering team can pick it up in the next sprint.
Produce the following files:
specs/003-payments/bugs.md — the structured bug report entry (create the file since none exists yet)specs/003-payments/tasks.md — with the fix tasks appended (do not modify existing entries)Also produce a bugfix-report.md at the root summarizing the bug ID assigned, the tasks created, and the approach taken.
The following files are provided as inputs. Extract them before beginning.
=============== FILE: specs/003-payments/tasks.md ===============
=============== FILE: CONSTITUTION.md ===============
Test-first development MUST be used for all features. Test specifications MUST be written before implementation begins. Modifying test assertions to make failing tests pass is PROHIBITED.
All payment state transitions MUST be idempotent. Duplicate charge prevention MUST be enforced at the service layer.
All payment events MUST be logged with full transaction context for dispute resolution.
Amendments require engineering lead approval and version increment. P1 and P2 are immutable.
=============== FILE: .specify/context.json =============== { "tdd_determination": "mandatory", "active_feature": "003-payments", "checklist_reviewed_at": "2026-02-15T10:30:00Z" }
=============== FILE: specs/003-payments/tests/features/process_payment.feature ===============
@US-001 Feature: Process Payment
@TS-001 @FR-001 @SC-001 @US-001 @P1 @acceptance Scenario: Successful payment processing Given a customer with a valid payment method When they submit a payment of $50.00 Then the payment is processed and status is "completed"
@TS-002 @FR-002 @SC-002 @US-001 @P1 @acceptance Scenario: Retry after network failure Given a payment that failed due to a network error When the system retries the payment Then only one charge is applied to the customer's account
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
rules
skills
iikit-00-constitution
scripts
dashboard
iikit-01-specify
iikit-02-plan
iikit-03-checklist
scripts
bash
dashboard
iikit-04-testify
iikit-05-tasks
iikit-06-analyze
iikit-07-implement
iikit-08-taskstoissues
iikit-bugfix
scripts
dashboard
iikit-clarify
iikit-core
references
scripts
bash
dashboard
powershell
templates