Skip to content

Commit df0a7c6

Browse files
cemmurphycemmurphy
committed
docs: establish project constitution v1.0.0 (core principles + governance framework)
- Add Full-Stack Integration, TDD, Auto-Generated Client, Docker-First, and Security principles - Define development workflow, quality standards, and security requirements - Update plan template with constitution check gates - Establish governance framework for future amendments
1 parent 632f1ac commit df0a7c6

17 files changed

+2255
-0
lines changed

‎.cursor/commands/analyze.md‎

Lines changed: 101 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,101 @@
1+
---
2+
description: Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
3+
---
4+
5+
The user input to you can be provided directly by the agent or as a command argument - you **MUST** consider it before proceeding with the prompt (if not empty).
6+
7+
User input:
8+
9+
$ARGUMENTS
10+
11+
Goal: Identify inconsistencies, duplications, ambiguities, and underspecified items across the three core artifacts (`spec.md`, `plan.md`, `tasks.md`) before implementation. This command MUST run only after `/tasks` has successfully produced a complete `tasks.md`.
12+
13+
STRICTLY READ-ONLY: Do **not** modify any files. Output a structured analysis report. Offer an optional remediation plan (user must explicitly approve before any follow-up editing commands would be invoked manually).
14+
15+
Constitution Authority: The project constitution (`.specify/memory/constitution.md`) is **non-negotiable** within this analysis scope. Constitution conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks—not dilution, reinterpretation, or silent ignoring of the principle. If a principle itself needs to change, that must occur in a separate, explicit constitution update outside `/analyze`.
16+
17+
Execution steps:
18+
19+
1. Run `.specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks` once from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS. Derive absolute paths:
20+
- SPEC = FEATURE_DIR/spec.md
21+
- PLAN = FEATURE_DIR/plan.md
22+
- TASKS = FEATURE_DIR/tasks.md
23+
Abort with an error message if any required file is missing (instruct the user to run missing prerequisite command).
24+
25+
2. Load artifacts:
26+
- Parse spec.md sections: Overview/Context, Functional Requirements, Non-Functional Requirements, User Stories, Edge Cases (if present).
27+
- Parse plan.md: Architecture/stack choices, Data Model references, Phases, Technical constraints.
28+
- Parse tasks.md: Task IDs, descriptions, phase grouping, parallel markers [P], referenced file paths.
29+
- Load constitution `.specify/memory/constitution.md` for principle validation.
30+
31+
3. Build internal semantic models:
32+
- Requirements inventory: Each functional + non-functional requirement with a stable key (derive slug based on imperative phrase; e.g., "User can upload file" -> `user-can-upload-file`).
33+
- User story/action inventory.
34+
- Task coverage mapping: Map each task to one or more requirements or stories (inference by keyword / explicit reference patterns like IDs or key phrases).
35+
- Constitution rule set: Extract principle names and any MUST/SHOULD normative statements.
36+
37+
4. Detection passes:
38+
A. Duplication detection:
39+
- Identify near-duplicate requirements. Mark lower-quality phrasing for consolidation.
40+
B. Ambiguity detection:
41+
- Flag vague adjectives (fast, scalable, secure, intuitive, robust) lacking measurable criteria.
42+
- Flag unresolved placeholders (TODO, TKTK, ???, <placeholder>, etc.).
43+
C. Underspecification:
44+
- Requirements with verbs but missing object or measurable outcome.
45+
- User stories missing acceptance criteria alignment.
46+
- Tasks referencing files or components not defined in spec/plan.
47+
D. Constitution alignment:
48+
- Any requirement or plan element conflicting with a MUST principle.
49+
- Missing mandated sections or quality gates from constitution.
50+
E. Coverage gaps:
51+
- Requirements with zero associated tasks.
52+
- Tasks with no mapped requirement/story.
53+
- Non-functional requirements not reflected in tasks (e.g., performance, security).
54+
F. Inconsistency:
55+
- Terminology drift (same concept named differently across files).
56+
- Data entities referenced in plan but absent in spec (or vice versa).
57+
- Task ordering contradictions (e.g., integration tasks before foundational setup tasks without dependency note).
58+
- Conflicting requirements (e.g., one requires to use Next.js while other says to use Vue as the framework).
59+
60+
5. Severity assignment heuristic:
61+
- CRITICAL: Violates constitution MUST, missing core spec artifact, or requirement with zero coverage that blocks baseline functionality.
62+
- HIGH: Duplicate or conflicting requirement, ambiguous security/performance attribute, untestable acceptance criterion.
63+
- MEDIUM: Terminology drift, missing non-functional task coverage, underspecified edge case.
64+
- LOW: Style/wording improvements, minor redundancy not affecting execution order.
65+
66+
6. Produce a Markdown report (no file writes) with sections:
67+
68+
### Specification Analysis Report
69+
| ID | Category | Severity | Location(s) | Summary | Recommendation |
70+
|----|----------|----------|-------------|---------|----------------|
71+
| A1 | Duplication | HIGH | spec.md:L120-134 | Two similar requirements ... | Merge phrasing; keep clearer version |
72+
(Add one row per finding; generate stable IDs prefixed by category initial.)
73+
74+
Additional subsections:
75+
- Coverage Summary Table:
76+
| Requirement Key | Has Task? | Task IDs | Notes |
77+
- Constitution Alignment Issues (if any)
78+
- Unmapped Tasks (if any)
79+
- Metrics:
80+
* Total Requirements
81+
* Total Tasks
82+
* Coverage % (requirements with >=1 task)
83+
* Ambiguity Count
84+
* Duplication Count
85+
* Critical Issues Count
86+
87+
7. At end of report, output a concise Next Actions block:
88+
- If CRITICAL issues exist: Recommend resolving before `/implement`.
89+
- If only LOW/MEDIUM: User may proceed, but provide improvement suggestions.
90+
- Provide explicit command suggestions: e.g., "Run /specify with refinement", "Run /plan to adjust architecture", "Manually edit tasks.md to add coverage for 'performance-metrics'".
91+
92+
8. Ask the user: "Would you like me to suggest concrete remediation edits for the top N issues?" (Do NOT apply them automatically.)
93+
94+
Behavior rules:
95+
- NEVER modify files.
96+
- NEVER hallucinate missing sections—if absent, report them.
97+
- KEEP findings deterministic: if rerun without changes, produce consistent IDs and counts.
98+
- LIMIT total findings in the main table to 50; aggregate remainder in a summarized overflow note.
99+
- If zero issues found, emit a success report with coverage statistics and proceed recommendation.
100+
101+
Context: $ARGUMENTS

‎.cursor/commands/clarify.md‎

Lines changed: 158 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,158 @@
1+
---
2+
description: Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
3+
---
4+
5+
The user input to you can be provided directly by the agent or as a command argument - you **MUST** consider it before proceeding with the prompt (if not empty).
6+
7+
User input:
8+
9+
$ARGUMENTS
10+
11+
Goal: Detect and reduce ambiguity or missing decision points in the active feature specification and record the clarifications directly in the spec file.
12+
13+
Note: This clarification workflow is expected to run (and be completed) BEFORE invoking `/plan`. If the user explicitly states they are skipping clarification (e.g., exploratory spike), you may proceed, but must warn that downstream rework risk increases.
14+
15+
Execution steps:
16+
17+
1. Run `.specify/scripts/bash/check-prerequisites.sh --json --paths-only` from repo root **once** (combined `--json --paths-only` mode / `-Json -PathsOnly`). Parse minimal JSON payload fields:
18+
- `FEATURE_DIR`
19+
- `FEATURE_SPEC`
20+
- (Optionally capture `IMPL_PLAN`, `TASKS` for future chained flows.)
21+
- If JSON parsing fails, abort and instruct user to re-run `/specify` or verify feature branch environment.
22+
23+
2. Load the current spec file. Perform a structured ambiguity & coverage scan using this taxonomy. For each category, mark status: Clear / Partial / Missing. Produce an internal coverage map used for prioritization (do not output raw map unless no questions will be asked).
24+
25+
Functional Scope & Behavior:
26+
- Core user goals & success criteria
27+
- Explicit out-of-scope declarations
28+
- User roles / personas differentiation
29+
30+
Domain & Data Model:
31+
- Entities, attributes, relationships
32+
- Identity & uniqueness rules
33+
- Lifecycle/state transitions
34+
- Data volume / scale assumptions
35+
36+
Interaction & UX Flow:
37+
- Critical user journeys / sequences
38+
- Error/empty/loading states
39+
- Accessibility or localization notes
40+
41+
Non-Functional Quality Attributes:
42+
- Performance (latency, throughput targets)
43+
- Scalability (horizontal/vertical, limits)
44+
- Reliability & availability (uptime, recovery expectations)
45+
- Observability (logging, metrics, tracing signals)
46+
- Security & privacy (authN/Z, data protection, threat assumptions)
47+
- Compliance / regulatory constraints (if any)
48+
49+
Integration & External Dependencies:
50+
- External services/APIs and failure modes
51+
- Data import/export formats
52+
- Protocol/versioning assumptions
53+
54+
Edge Cases & Failure Handling:
55+
- Negative scenarios
56+
- Rate limiting / throttling
57+
- Conflict resolution (e.g., concurrent edits)
58+
59+
Constraints & Tradeoffs:
60+
- Technical constraints (language, storage, hosting)
61+
- Explicit tradeoffs or rejected alternatives
62+
63+
Terminology & Consistency:
64+
- Canonical glossary terms
65+
- Avoided synonyms / deprecated terms
66+
67+
Completion Signals:
68+
- Acceptance criteria testability
69+
- Measurable Definition of Done style indicators
70+
71+
Misc / Placeholders:
72+
- TODO markers / unresolved decisions
73+
- Ambiguous adjectives ("robust", "intuitive") lacking quantification
74+
75+
For each category with Partial or Missing status, add a candidate question opportunity unless:
76+
- Clarification would not materially change implementation or validation strategy
77+
- Information is better deferred to planning phase (note internally)
78+
79+
3. Generate (internally) a prioritized queue of candidate clarification questions (maximum 5). Do NOT output them all at once. Apply these constraints:
80+
- Maximum of 5 total questions across the whole session.
81+
- Each question must be answerable with EITHER:
82+
* A short multiple‑choice selection (2–5 distinct, mutually exclusive options), OR
83+
* A one-word / short‑phrase answer (explicitly constrain: "Answer in <=5 words").
84+
- Only include questions whose answers materially impact architecture, data modeling, task decomposition, test design, UX behavior, operational readiness, or compliance validation.
85+
- Ensure category coverage balance: attempt to cover the highest impact unresolved categories first; avoid asking two low-impact questions when a single high-impact area (e.g., security posture) is unresolved.
86+
- Exclude questions already answered, trivial stylistic preferences, or plan-level execution details (unless blocking correctness).
87+
- Favor clarifications that reduce downstream rework risk or prevent misaligned acceptance tests.
88+
- If more than 5 categories remain unresolved, select the top 5 by (Impact * Uncertainty) heuristic.
89+
90+
4. Sequential questioning loop (interactive):
91+
- Present EXACTLY ONE question at a time.
92+
- For multiple‑choice questions render options as a Markdown table:
93+
94+
| Option | Description |
95+
|--------|-------------|
96+
| A | <Option A description> |
97+
| B | <Option B description> |
98+
| C | <Option C description> | (add D/E as needed up to 5)
99+
| Short | Provide a different short answer (<=5 words) | (Include only if free-form alternative is appropriate)
100+
101+
- For short‑answer style (no meaningful discrete options), output a single line after the question: `Format: Short answer (<=5 words)`.
102+
- After the user answers:
103+
* Validate the answer maps to one option or fits the <=5 word constraint.
104+
* If ambiguous, ask for a quick disambiguation (count still belongs to same question; do not advance).
105+
* Once satisfactory, record it in working memory (do not yet write to disk) and move to the next queued question.
106+
- Stop asking further questions when:
107+
* All critical ambiguities resolved early (remaining queued items become unnecessary), OR
108+
* User signals completion ("done", "good", "no more"), OR
109+
* You reach 5 asked questions.
110+
- Never reveal future queued questions in advance.
111+
- If no valid questions exist at start, immediately report no critical ambiguities.
112+
113+
5. Integration after EACH accepted answer (incremental update approach):
114+
- Maintain in-memory representation of the spec (loaded once at start) plus the raw file contents.
115+
- For the first integrated answer in this session:
116+
* Ensure a `## Clarifications` section exists (create it just after the highest-level contextual/overview section per the spec template if missing).
117+
* Under it, create (if not present) a `### Session YYYY-MM-DD` subheading for today.
118+
- Append a bullet line immediately after acceptance: `- Q: <question> → A: <final answer>`.
119+
- Then immediately apply the clarification to the most appropriate section(s):
120+
* Functional ambiguity → Update or add a bullet in Functional Requirements.
121+
* User interaction / actor distinction → Update User Stories or Actors subsection (if present) with clarified role, constraint, or scenario.
122+
* Data shape / entities → Update Data Model (add fields, types, relationships) preserving ordering; note added constraints succinctly.
123+
* Non-functional constraint → Add/modify measurable criteria in Non-Functional / Quality Attributes section (convert vague adjective to metric or explicit target).
124+
* Edge case / negative flow → Add a new bullet under Edge Cases / Error Handling (or create such subsection if template provides placeholder for it).
125+
* Terminology conflict → Normalize term across spec; retain original only if necessary by adding `(formerly referred to as "X")` once.
126+
- If the clarification invalidates an earlier ambiguous statement, replace that statement instead of duplicating; leave no obsolete contradictory text.
127+
- Save the spec file AFTER each integration to minimize risk of context loss (atomic overwrite).
128+
- Preserve formatting: do not reorder unrelated sections; keep heading hierarchy intact.
129+
- Keep each inserted clarification minimal and testable (avoid narrative drift).
130+
131+
6. Validation (performed after EACH write plus final pass):
132+
- Clarifications session contains exactly one bullet per accepted answer (no duplicates).
133+
- Total asked (accepted) questions ≤ 5.
134+
- Updated sections contain no lingering vague placeholders the new answer was meant to resolve.
135+
- No contradictory earlier statement remains (scan for now-invalid alternative choices removed).
136+
- Markdown structure valid; only allowed new headings: `## Clarifications`, `### Session YYYY-MM-DD`.
137+
- Terminology consistency: same canonical term used across all updated sections.
138+
139+
7. Write the updated spec back to `FEATURE_SPEC`.
140+
141+
8. Report completion (after questioning loop ends or early termination):
142+
- Number of questions asked & answered.
143+
- Path to updated spec.
144+
- Sections touched (list names).
145+
- Coverage summary table listing each taxonomy category with Status: Resolved (was Partial/Missing and addressed), Deferred (exceeds question quota or better suited for planning), Clear (already sufficient), Outstanding (still Partial/Missing but low impact).
146+
- If any Outstanding or Deferred remain, recommend whether to proceed to `/plan` or run `/clarify` again later post-plan.
147+
- Suggested next command.
148+
149+
Behavior rules:
150+
- If no meaningful ambiguities found (or all potential questions would be low-impact), respond: "No critical ambiguities detected worth formal clarification." and suggest proceeding.
151+
- If spec file missing, instruct user to run `/specify` first (do not create a new spec here).
152+
- Never exceed 5 total asked questions (clarification retries for a single question do not count as new questions).
153+
- Avoid speculative tech stack questions unless the absence blocks functional clarity.
154+
- Respect user early termination signals ("stop", "done", "proceed").
155+
- If no questions asked due to full coverage, output a compact coverage summary (all categories Clear) then suggest advancing.
156+
- If quota reached with unresolved high-impact categories remaining, explicitly flag them under Deferred with rationale.
157+
158+
Context for prioritization: $ARGUMENTS

0 commit comments

Comments
 (0)