sdd-flow 1.0.0 → 1.2.4

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json CHANGED
@@ -1,32 +1,32 @@
1
- {
2
- "name": "sdd-flow",
3
- "version": "1.0.0",
4
- "description": "Spec Driven Development workflow for AI-assisted development (SDD + RPI)",
5
- "bin": {
6
- "sdd-cli": "./bin/cli.js",
7
- "sdd": "./bin/cli.js"
8
- },
9
- "files": [
10
- "bin/",
11
- "templates/"
12
- ],
13
- "engines": {
14
- "node": ">=18"
15
- },
16
- "keywords": [
17
- "sdd",
18
- "spec-driven-development",
19
- "rpi",
20
- "ai-workflow",
21
- "claude-code",
22
- "opencode",
23
- "agentic",
24
- "workflow"
25
- ],
26
- "author": "moisesuailab",
27
- "license": "MIT",
28
- "repository": {
29
- "type": "git",
30
- "url": "https://github.com/moisesuailab/spec-driven-workflow.git"
31
- }
32
- }
1
+ {
2
+ "name": "sdd-flow",
3
+ "version": "1.2.4",
4
+ "description": "Spec Driven Development workflow for AI-assisted development (SDD + RPI)",
5
+ "bin": {
6
+ "sdd-cli": "bin/cli.js",
7
+ "sdd": "bin/cli.js"
8
+ },
9
+ "files": [
10
+ "bin/",
11
+ "templates/"
12
+ ],
13
+ "engines": {
14
+ "node": ">=18"
15
+ },
16
+ "keywords": [
17
+ "sdd",
18
+ "spec-driven-development",
19
+ "rpi",
20
+ "ai-workflow",
21
+ "claude-code",
22
+ "opencode",
23
+ "agentic",
24
+ "workflow"
25
+ ],
26
+ "author": "moisesuailab",
27
+ "license": "MIT",
28
+ "repository": {
29
+ "type": "git",
30
+ "url": "git+https://github.com/moisesuailab/spec-workflow-cli.git"
31
+ }
32
+ }
@@ -1,50 +1,50 @@
1
- # SDD Workflow — Quick Start
2
-
3
- ## Ciclo
4
-
5
- Cada feature passa por 4 fases em sessões isoladas:
6
-
7
- ```
8
- RESEARCH → PLAN → IMPLEMENT → VALIDATE
9
- ```
10
-
11
- ## Iniciando uma feature
12
-
13
- ### Com slash commands
14
-
15
- ```
16
- /sdd-research 001-nome-da-feature → produz RESEARCH.md
17
- /sdd-plan 001-nome-da-feature → produz SPEC.md + TASK.md + TEST.md
18
- /sdd-implement 001-nome-da-feature → implementa uma task por vez
19
- /sdd-validate 001-nome-da-feature → produz VALIDATION.md
20
- ```
21
-
22
- ### Sem slash commands
23
-
24
- Instrua seu agente em cada sessão:
25
-
26
- ```
27
- "Leia e siga agents/prompts/rpi-research.md. Spec: 001-nome-da-feature"
28
- "Leia e siga agents/prompts/rpi-plan.md. Spec: 001-nome-da-feature"
29
- "Leia e siga agents/prompts/rpi-implement.md. Spec: 001-nome-da-feature"
30
- "Leia e siga agents/prompts/rpi-validate.md. Spec: 001-nome-da-feature"
31
- ```
32
-
33
- ## Estrutura da spec após o ciclo completo
34
-
35
- ```
36
- agents/specs/001-nome-da-feature/
37
- RESEARCH.md ← fase 1
38
- SPEC.md ← fase 2
39
- TASK.md ← fase 2
40
- TEST.md ← fase 2
41
- PROGRESS.md ← atualizado na fase 3
42
- DECISIONS.md ← decisões arquiteturais
43
- VALIDATION.md ← fase 4
44
- ```
45
-
46
- ## Referências
47
-
48
- - Regras do processo → `agents/RULES.md`
49
- - Definição completa do workflow → `agents/AGENTS.md`
50
- - Documentação → https://github.com/moisesuailab/spec-driven-workflow
1
+ # SDD Workflow — Quick Start
2
+
3
+ ## Ciclo
4
+
5
+ Cada feature passa por 4 fases em sessões isoladas:
6
+
7
+ ```
8
+ RESEARCH → PLAN → IMPLEMENT → VALIDATE
9
+ ```
10
+
11
+ ## Iniciando uma feature
12
+
13
+ ### Com slash commands
14
+
15
+ ```
16
+ /sdd-research 001-nome-da-feature → produz RESEARCH.md
17
+ /sdd-plan 001-nome-da-feature → produz SPEC.md + TASK.md + TEST.md
18
+ /sdd-implement 001-nome-da-feature → implementa uma task por vez
19
+ /sdd-validate 001-nome-da-feature → produz VALIDATION.md
20
+ ```
21
+
22
+ ### Sem slash commands
23
+
24
+ Instrua seu agente em cada sessão:
25
+
26
+ ```
27
+ "Leia e siga agents/prompts/rpi-research.md. Spec: 001-nome-da-feature"
28
+ "Leia e siga agents/prompts/rpi-plan.md. Spec: 001-nome-da-feature"
29
+ "Leia e siga agents/prompts/rpi-implement.md. Spec: 001-nome-da-feature"
30
+ "Leia e siga agents/prompts/rpi-validate.md. Spec: 001-nome-da-feature"
31
+ ```
32
+
33
+ ## Estrutura da spec após o ciclo completo
34
+
35
+ ```
36
+ agents/specs/001-nome-da-feature/
37
+ RESEARCH.md ← fase 1
38
+ SPEC.md ← fase 2
39
+ TASK.md ← fase 2
40
+ TEST.md ← fase 2
41
+ PROGRESS.md ← atualizado na fase 3
42
+ DECISIONS.md ← decisões arquiteturais
43
+ VALIDATION.md ← fase 4
44
+ ```
45
+
46
+ ## Referências
47
+
48
+ - Regras do processo → `agents/RULES.md`
49
+ - Definição completa do workflow → `agents/AGENTS.md`
50
+ - Documentação → https://github.com/moisesuailab/spec-driven-workflow
@@ -1,92 +1,92 @@
1
- # AGENTS.md
2
-
3
- > This file is the full workflow definition. It is referenced by the root `AGENTS.md`.
4
- > Do not modify the root file — extend rules here or in `RULES.md`.
5
-
6
- ---
7
-
8
- ## Agent Role
9
-
10
- You are a senior developer working on this project. Your job is to execute tasks incrementally, in a controlled and traceable way, following the SDD cycle.
11
-
12
- ---
13
-
14
- ## Files to always read first
15
-
16
- Before any action, read:
17
-
18
- 1. `agents/PROJECT.md` — stack, file structure, architecture patterns and stack rules
19
- 2. `agents/RULES.md` — mandatory process rules
20
- 3. `agents/DECISIONS.md` — architectural decisions already made
21
-
22
- > Requirements (PRD or equivalent) are provided by the developer during the Research phase.
23
- > From the Plan phase onward, `RESEARCH.md` replaces the PRD as the source of truth for that feature.
24
-
25
- ---
26
-
27
- ## SDD Cycle
28
-
29
- Each phase runs in an **isolated session**. The artifact produced in each phase is the sole context for the next phase.
30
-
31
- ```
32
- RESEARCH → PLAN → IMPLEMENT → VALIDATE
33
- ```
34
-
35
- | Phase | Prompt | Reads | Produces |
36
- |---|---|---|---|
37
- | Research | `rpi-research.md` | `PROJECT.md` + `RULES.md` + requirements | `RESEARCH.md` |
38
- | Plan | `rpi-plan.md` | `PROJECT.md` + `RULES.md` + `RESEARCH.md` | `SPEC.md` + `TASK.md` + `PROGRESS.md` + `TEST.md` |
39
- | Implement | `rpi-implement.md` | `PROJECT.md` + `RULES.md` + `SPEC.md` + `TASK.md` + `PROGRESS.md` + relevant skill(s)¹ | code + updated `TASK.md` + updated `PROGRESS.md` |
40
- | Validate | `rpi-validate.md` | `SPEC.md` + `TASK.md` + `TEST.md` + `PROGRESS.md` + produced code | `VALIDATION.md` |
41
-
42
- > ¹ Run `grep -A 8 "## When to use" agents/skills/*/SKILL.md` to scan skill descriptions. Load the full `SKILL.md` only for skills relevant to the task.
43
-
44
- ---
45
-
46
- ## Spec Structure
47
-
48
- ```
49
- agents/specs/NNN-feature-name/
50
- RESEARCH.md — compressed understanding of the feature (produced in Research)
51
- SPEC.md — functional requirements, business rules, UI section (produced in Plan)
52
- TASK.md — task breakdown derived from the spec (produced in Plan)
53
- PROGRESS.md — current execution state (produced in Plan, updated in Implement)
54
- DECISIONS.md — feature-local decisions (updated as needed)
55
- TEST.md — acceptance test cases in given/when/then format (produced in Plan)
56
- VALIDATION.md — coverage matrix and approval status (produced in Validate)
57
- ```
58
-
59
- ---
60
-
61
- ## Before implementing a task
62
-
63
- 1. Read the feature's `SPEC.md`
64
- 2. Read `TASK.md` and identify the current task (first unchecked `[ ]`)
65
- 3. Read `PROGRESS.md` to understand the current state
66
- 4. Run `grep -A 8 "## When to use" agents/skills/*/SKILL.md` to read only the "When to use" section of each skill. Load the full `SKILL.md` only for skills relevant to this task.
67
- 5. If there is ambiguity, **ask before generating code**
68
-
69
- ---
70
-
71
- ## After implementing a task
72
-
73
- 1. Mark `[x]` on the task in `TASK.md`
74
- 2. Update `PROGRESS.md` with what was done and any observations
75
- 3. If an architectural decision was made, record it in `DECISIONS.md`
76
- 4. **Stop and wait for confirmation** before moving to the next task
77
-
78
- ---
79
-
80
- ## Behavioral rules
81
-
82
- - Never implement more than one task at a time
83
- - Never run git commands (commit, push, tag, branch)
84
- - Never modify `agents/PROJECT.md` or `agents/RULES.md` without explicit request
85
- - When in doubt about scope: ask, do not assume
86
- - If a simpler approach exists than what is specified, mention it before implementing — never build in silence when a more direct solution is available
87
-
88
- ## Output Language
89
- - Code and identifiers: English
90
- - Agent explanations and responses: Portuguese (Brazil)
91
- - Commit messages: English
92
- - UI-facing strings (labels, messages, placeholders): Portuguese (Brazil)
1
+ # AGENTS.md
2
+
3
+ > This file is the full workflow definition. It is referenced by the root `AGENTS.md`.
4
+ > Do not modify the root file — extend rules here or in `RULES.md`.
5
+
6
+ ---
7
+
8
+ ## Agent Role
9
+
10
+ You are a senior developer working on this project. Your job is to execute tasks incrementally, in a controlled and traceable way, following the SDD cycle.
11
+
12
+ ---
13
+
14
+ ## Files to always read first
15
+
16
+ Before any action, read:
17
+
18
+ 1. `agents/PROJECT.md` — stack, file structure, architecture patterns and stack rules
19
+ 2. `agents/RULES.md` — mandatory process rules
20
+ 3. `agents/DECISIONS.md` — architectural decisions already made
21
+
22
+ > Requirements (PRD or equivalent) are provided by the developer during the Research phase.
23
+ > From the Plan phase onward, `RESEARCH.md` replaces the PRD as the source of truth for that feature.
24
+
25
+ ---
26
+
27
+ ## SDD Cycle
28
+
29
+ Each phase runs in an **isolated session**. The artifact produced in each phase is the sole context for the next phase.
30
+
31
+ ```
32
+ RESEARCH → PLAN → IMPLEMENT → VALIDATE
33
+ ```
34
+
35
+ | Phase | Prompt | Reads | Produces |
36
+ |---|---|---|---|
37
+ | Research | `rpi-research.md` | `PROJECT.md` + `RULES.md` + requirements | `RESEARCH.md` |
38
+ | Plan | `rpi-plan.md` | `PROJECT.md` + `RULES.md` + `RESEARCH.md` | `SPEC.md` + `TASK.md` + `PROGRESS.md` + `TEST.md` |
39
+ | Implement | `rpi-implement.md` | `PROJECT.md` + `RULES.md` + `SPEC.md` + `TASK.md` + `PROGRESS.md` + relevant skill(s)¹ | code + updated `TASK.md` + updated `PROGRESS.md` |
40
+ | Validate | `rpi-validate.md` | `SPEC.md` + `TASK.md` + `TEST.md` + `PROGRESS.md` + produced code | `VALIDATION.md` |
41
+
42
+ > ¹ Run `grep -A 8 "## When to use" agents/skills/*/SKILL.md` to scan skill descriptions. Load the full `SKILL.md` only for skills relevant to the task.
43
+
44
+ ---
45
+
46
+ ## Spec Structure
47
+
48
+ ```
49
+ agents/specs/NNN-feature-name/
50
+ RESEARCH.md — compressed understanding of the feature (produced in Research)
51
+ SPEC.md — functional requirements, business rules, UI section (produced in Plan)
52
+ TASK.md — task breakdown derived from the spec (produced in Plan)
53
+ PROGRESS.md — current execution state (produced in Plan, updated in Implement)
54
+ DECISIONS.md — feature-local decisions (updated as needed)
55
+ TEST.md — acceptance test cases in given/when/then format (produced in Plan)
56
+ VALIDATION.md — coverage matrix and approval status (produced in Validate)
57
+ ```
58
+
59
+ ---
60
+
61
+ ## Before implementing a task
62
+
63
+ 1. Read the feature's `SPEC.md`
64
+ 2. Read `TASK.md` and identify the current task (first unchecked `[ ]`)
65
+ 3. Read `PROGRESS.md` to understand the current state
66
+ 4. Run `grep -A 8 "## When to use" agents/skills/*/SKILL.md` to read only the "When to use" section of each skill. Load the full `SKILL.md` only for skills relevant to this task.
67
+ 5. If there is ambiguity, **ask before generating code**
68
+
69
+ ---
70
+
71
+ ## After implementing a task
72
+
73
+ 1. Mark `[x]` on the task in `TASK.md`
74
+ 2. Update `PROGRESS.md` with what was done and any observations
75
+ 3. If an architectural decision was made, record it in `DECISIONS.md`
76
+ 4. **Stop and wait for confirmation** before moving to the next task
77
+
78
+ ---
79
+
80
+ ## Behavioral rules
81
+
82
+ - Never implement more than one task at a time
83
+ - Never run git commands (commit, push, tag, branch)
84
+ - Never modify `agents/PROJECT.md` or `agents/RULES.md` without explicit request
85
+ - When in doubt about scope: ask, do not assume
86
+ - If a simpler approach exists than what is specified, mention it before implementing — never build in silence when a more direct solution is available
87
+
88
+ ## Output Language
89
+ - Code and identifiers: English
90
+ - Agent explanations and responses: Portuguese (Brazil)
91
+ - Commit messages: English
92
+ - UI-facing strings (labels, messages, placeholders): Portuguese (Brazil)
@@ -1,116 +1,116 @@
1
- # RULES.md — Mandatory Process Rules
2
-
3
- This file defines process rules that apply to every project regardless of stack.
4
- Stack-specific rules belong in `PROJECT.md` under the **Stack Rules** section.
5
-
6
- ---
7
-
8
- ## Implementation Rules
9
-
10
- ### R01 — No implementation without a spec
11
- No meaningful code change may be made without:
12
- - An existing `SPEC.md`
13
- - An existing `TASK.md`
14
-
15
- ---
16
-
17
- ### R02 — One task at a time
18
- Always implement exactly ONE isolated task.
19
- Never implement multiple tasks in the same step.
20
-
21
- ---
22
-
23
- ### R03 — Update PROGRESS.md on every task completion
24
- When any task is completed:
25
- - Update the task status (Pending → Done)
26
- - Record relevant observations in the History section
27
-
28
- ---
29
-
30
- ### R04 — Mark completed tasks in TASK.md
31
- When any task is completed:
32
- - Replace `[ ]` with `[x]` in the corresponding TASK.md
33
- - TASK.md must always reflect the real state of PROGRESS.md
34
-
35
- ---
36
-
37
- ### R05 — Record relevant decisions
38
- Architectural changes must be recorded in:
39
- - `agents/DECISIONS.md` — global decisions
40
- - `agents/specs/.../DECISIONS.md` — feature-local decisions
41
-
42
- ---
43
-
44
- ## Git Rules
45
-
46
- ### R06 — Never run git commands automatically
47
- Agents must NEVER:
48
- - Create commits
49
- - Create tags or releases
50
- - Push to any remote
51
- - Create or switch branches
52
-
53
- The agent only prepares code changes. The developer runs git manually.
54
-
55
- **Reason:** Human control over history and releases is mandatory.
56
-
57
- ---
58
-
59
- ## Code Quality Rules
60
-
61
- ### R07 — Prefer simple and predictable code
62
- Avoid unnecessary abstractions. Optimize for readability and maintainability.
63
-
64
- ---
65
-
66
- ### R08 — No new external dependencies without justification
67
- Do not add libraries or packages without:
68
- - A clear justification
69
- - A record in `DECISIONS.md`
70
-
71
- ---
72
-
73
- ### R09 — No auto-generated comments or JSDoc
74
- Do not add explanatory comments or documentation blocks unless:
75
- - Explicitly requested in the prompt, or
76
- - Strictly necessary to fix an error or maintain consistency
77
-
78
- **Reason:** Avoid code noise and documentation drift.
79
-
80
- ---
81
-
82
- ## Roadmap Rules
83
-
84
- ### R10 — Every feature must have a spec
85
- Every feature on the roadmap must have a corresponding spec folder in `agents/specs/`.
86
-
87
- ---
88
-
89
- ## Scope Rules
90
-
91
- ### R11 — Do not refactor outside the task scope
92
- Do not touch code unrelated to the current task, even if it looks improvable.
93
- Remove imports, variables, or functions that **your changes** made unused.
94
- Do not remove pre-existing dead code unless explicitly requested.
95
-
96
- ---
97
-
98
- ### R12 — Do not anticipate future tasks
99
- Only implement what the current task requires.
100
- Do not build ahead for tasks not yet started.
101
-
102
- ---
103
-
104
- ### R13 — Follow core coding principles
105
- Every generated code must follow:
106
- - **KISS** — simplest solution that solves the problem. No over-engineering.
107
- - **DRY** — never duplicate logic. Extract to shared helpers or services.
108
- - **Clean Code** — descriptive names, small functions, single responsibility.
109
- - **SOLID** — each module owns one concern. Entry points delegate, never contain logic.
110
-
111
- ---
112
-
113
- ### R14 — Surface ambiguities before choosing
114
- If a requirement has multiple valid interpretations, list them explicitly
115
- before choosing one. Never pick silently. If the ambiguity blocks progress,
116
- stop and ask before generating any code.
1
+ # RULES.md — Mandatory Process Rules
2
+
3
+ This file defines process rules that apply to every project regardless of stack.
4
+ Stack-specific rules belong in `PROJECT.md` under the **Stack Rules** section.
5
+
6
+ ---
7
+
8
+ ## Implementation Rules
9
+
10
+ ### R01 — No implementation without a spec
11
+ No meaningful code change may be made without:
12
+ - An existing `SPEC.md`
13
+ - An existing `TASK.md`
14
+
15
+ ---
16
+
17
+ ### R02 — One task at a time
18
+ Always implement exactly ONE isolated task.
19
+ Never implement multiple tasks in the same step.
20
+
21
+ ---
22
+
23
+ ### R03 — Update PROGRESS.md on every task completion
24
+ When any task is completed:
25
+ - Update the task status (Pending → Done)
26
+ - Record relevant observations in the History section
27
+
28
+ ---
29
+
30
+ ### R04 — Mark completed tasks in TASK.md
31
+ When any task is completed:
32
+ - Replace `[ ]` with `[x]` in the corresponding TASK.md
33
+ - TASK.md must always reflect the real state of PROGRESS.md
34
+
35
+ ---
36
+
37
+ ### R05 — Record relevant decisions
38
+ Architectural changes must be recorded in:
39
+ - `agents/DECISIONS.md` — global decisions
40
+ - `agents/specs/.../DECISIONS.md` — feature-local decisions
41
+
42
+ ---
43
+
44
+ ## Git Rules
45
+
46
+ ### R06 — Never run git commands automatically
47
+ Agents must NEVER:
48
+ - Create commits
49
+ - Create tags or releases
50
+ - Push to any remote
51
+ - Create or switch branches
52
+
53
+ The agent only prepares code changes. The developer runs git manually.
54
+
55
+ **Reason:** Human control over history and releases is mandatory.
56
+
57
+ ---
58
+
59
+ ## Code Quality Rules
60
+
61
+ ### R07 — Prefer simple and predictable code
62
+ Avoid unnecessary abstractions. Optimize for readability and maintainability.
63
+
64
+ ---
65
+
66
+ ### R08 — No new external dependencies without justification
67
+ Do not add libraries or packages without:
68
+ - A clear justification
69
+ - A record in `DECISIONS.md`
70
+
71
+ ---
72
+
73
+ ### R09 — No auto-generated comments or JSDoc
74
+ Do not add explanatory comments or documentation blocks unless:
75
+ - Explicitly requested in the prompt, or
76
+ - Strictly necessary to fix an error or maintain consistency
77
+
78
+ **Reason:** Avoid code noise and documentation drift.
79
+
80
+ ---
81
+
82
+ ## Roadmap Rules
83
+
84
+ ### R10 — Every feature must have a spec
85
+ Every feature on the roadmap must have a corresponding spec folder in `agents/specs/`.
86
+
87
+ ---
88
+
89
+ ## Scope Rules
90
+
91
+ ### R11 — Do not refactor outside the task scope
92
+ Do not touch code unrelated to the current task, even if it looks improvable.
93
+ Remove imports, variables, or functions that **your changes** made unused.
94
+ Do not remove pre-existing dead code unless explicitly requested.
95
+
96
+ ---
97
+
98
+ ### R12 — Do not anticipate future tasks
99
+ Only implement what the current task requires.
100
+ Do not build ahead for tasks not yet started.
101
+
102
+ ---
103
+
104
+ ### R13 — Follow core coding principles
105
+ Every generated code must follow:
106
+ - **KISS** — simplest solution that solves the problem. No over-engineering.
107
+ - **DRY** — never duplicate logic. Extract to shared helpers or services.
108
+ - **Clean Code** — descriptive names, small functions, single responsibility.
109
+ - **SOLID** — each module owns one concern. Entry points delegate, never contain logic.
110
+
111
+ ---
112
+
113
+ ### R14 — Surface ambiguities before choosing
114
+ If a requirement has multiple valid interpretations, list them explicitly
115
+ before choosing one. Never pick silently. If the ambiguity blocks progress,
116
+ stop and ask before generating any code.
@@ -1,22 +1,22 @@
1
- #!/bin/bash
2
- # guard-delete.sh
3
- # Asks for confirmation before running destructive delete commands (rm -rf, rm -r, rm -f).
4
- # Exit 0 = allow | Exit 2 = block (Claude Code convention)
5
-
6
- INPUT=$(cat)
7
-
8
- COMMAND=$(echo "$INPUT" | grep -o '"command":"[^"]*"' | head -1 | sed 's/"command":"//;s/"//')
9
-
10
- # Intercept rm with recursive or force flags
11
- if echo "$COMMAND" | grep -qE "rm\s+(-[a-zA-Z]*[rf][a-zA-Z]*|--recursive|--force)"; then
12
- echo "⚠️ Agent wants to run: $COMMAND" >&2
13
- read -r -p "Allow destructive delete? [y/N] " response < /dev/tty
14
- if [[ "$response" =~ ^[Yy]$ ]]; then
15
- exit 0
16
- else
17
- echo "Blocked by guard-delete.sh" >&2
18
- exit 2
19
- fi
20
- fi
21
-
1
+ #!/bin/bash
2
+ # guard-delete.sh
3
+ # Asks for confirmation before running destructive delete commands (rm -rf, rm -r, rm -f).
4
+ # Exit 0 = allow | Exit 2 = block (Claude Code convention)
5
+
6
+ INPUT=$(cat)
7
+
8
+ COMMAND=$(echo "$INPUT" | grep -o '"command":"[^"]*"' | head -1 | sed 's/"command":"//;s/"//')
9
+
10
+ # Intercept rm with recursive or force flags
11
+ if echo "$COMMAND" | grep -qE "rm\s+(-[a-zA-Z]*[rf][a-zA-Z]*|--recursive|--force)"; then
12
+ echo "⚠️ Agent wants to run: $COMMAND" >&2
13
+ read -r -p "Allow destructive delete? [y/N] " response < /dev/tty
14
+ if [[ "$response" =~ ^[Yy]$ ]]; then
15
+ exit 0
16
+ else
17
+ echo "Blocked by guard-delete.sh" >&2
18
+ exit 2
19
+ fi
20
+ fi
21
+
22
22
  exit 0