@curdx/flow 2.2.4 β 2.2.5
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/.claude-plugin/marketplace.json +3 -2
- package/.claude-plugin/plugin.json +2 -1
- package/CHANGELOG.md +4 -566
- package/README.md +47 -113
- package/agents/flow-adversary.md +1 -0
- package/agents/flow-architect.md +9 -36
- package/agents/flow-brownfield-analyst.md +7 -18
- package/agents/flow-debugger.md +1 -0
- package/agents/flow-edge-hunter.md +1 -0
- package/agents/flow-executor.md +1 -0
- package/agents/flow-planner.md +11 -37
- package/agents/flow-product-designer.md +9 -41
- package/agents/flow-qa-engineer.md +1 -0
- package/agents/flow-researcher.md +9 -45
- package/agents/flow-reviewer.md +1 -0
- package/agents/flow-security-auditor.md +1 -0
- package/agents/flow-triage-analyst.md +1 -0
- package/agents/flow-ui-researcher.md +1 -0
- package/agents/flow-ux-designer.md +1 -0
- package/agents/flow-verifier.md +1 -0
- package/cli/install-companions.js +8 -8
- package/gates/coverage-audit-gate.md +1 -3
- package/gates/tdd-gate.md +0 -6
- package/gates/verification-gate.md +1 -5
- package/knowledge/artifact-output-discipline.md +24 -0
- package/knowledge/artifact-summary-contracts.md +50 -0
- package/knowledge/execution-strategies.md +6 -4
- package/knowledge/poc-first-workflow.md +2 -6
- package/knowledge/spec-driven-development.md +0 -4
- package/knowledge/systematic-debugging.md +0 -6
- package/knowledge/two-stage-review.md +8 -6
- package/knowledge/wave-execution.md +2 -1
- package/package.json +2 -2
- package/schemas/agent-frontmatter.schema.json +4 -0
- package/skills/brownfield-index/SKILL.md +14 -20
- package/skills/brownfield-index/references/applicability.md +12 -0
- package/skills/brownfield-index/references/handoff.md +8 -0
- package/skills/brownfield-index/references/index-contract.md +10 -0
- package/skills/browser-qa/SKILL.md +15 -35
- package/skills/browser-qa/references/handoff.md +6 -0
- package/skills/browser-qa/references/prerequisites.md +10 -0
- package/skills/browser-qa/references/qa-contract.md +20 -0
- package/skills/cancel/SKILL.md +20 -61
- package/skills/cancel/references/destructive-mode.md +17 -0
- package/skills/cancel/references/reporting.md +18 -0
- package/skills/cancel/references/state-recovery.md +30 -0
- package/skills/cancel/references/target-resolution.md +7 -0
- package/skills/debug/SKILL.md +23 -87
- package/skills/debug/references/context-gathering.md +11 -0
- package/skills/debug/references/failure-guard.md +25 -0
- package/skills/debug/references/intake.md +12 -0
- package/skills/debug/references/phase-workflow.md +34 -0
- package/skills/debug/references/reporting.md +20 -0
- package/skills/epic/SKILL.md +18 -50
- package/skills/epic/references/epic-artifacts.md +20 -0
- package/skills/epic/references/epic-intake.md +9 -0
- package/skills/epic/references/slice-handoff.md +16 -0
- package/skills/fast/SKILL.md +34 -102
- package/skills/fast/references/applicability.md +25 -0
- package/skills/fast/references/clarification.md +20 -0
- package/skills/fast/references/execution-contract.md +56 -0
- package/skills/help/SKILL.md +26 -132
- package/skills/help/references/dispatch.md +20 -0
- package/skills/help/references/overview.md +39 -0
- package/skills/help/references/troubleshoot.md +47 -0
- package/skills/help/references/workflow.md +37 -0
- package/skills/implement/SKILL.md +61 -237
- package/skills/implement/references/error-recovery.md +36 -0
- package/skills/implement/references/linear-execution.md +32 -0
- package/skills/implement/references/preflight.md +43 -0
- package/skills/implement/references/progress-contract.md +32 -0
- package/skills/implement/references/state-init.md +33 -0
- package/skills/implement/references/stop-hook-execution.md +36 -0
- package/skills/implement/references/strategy-router.md +38 -0
- package/skills/implement/references/subagent-execution.md +43 -0
- package/skills/init/SKILL.md +26 -95
- package/skills/init/references/gitignore-and-health.md +26 -0
- package/skills/init/references/next-steps.md +22 -0
- package/skills/init/references/preflight.md +15 -0
- package/skills/init/references/scaffold-contract.md +27 -0
- package/skills/review/SKILL.md +45 -153
- package/skills/review/references/optional-passes.md +48 -0
- package/skills/review/references/preflight.md +38 -0
- package/skills/review/references/report-contract.md +49 -0
- package/skills/review/references/reporting.md +20 -0
- package/skills/review/references/stage-execution.md +32 -0
- package/skills/security-audit/SKILL.md +16 -34
- package/skills/security-audit/references/audit-contract.md +21 -0
- package/skills/security-audit/references/gate-handoff.md +8 -0
- package/skills/security-audit/references/scope-and-depth.md +9 -0
- package/skills/spec/SKILL.md +55 -182
- package/skills/spec/references/artifact-landing.md +31 -0
- package/skills/spec/references/phase-execution.md +50 -0
- package/skills/spec/references/planning-review.md +31 -0
- package/skills/spec/references/preflight-and-routing.md +46 -0
- package/skills/spec/references/reporting.md +21 -0
- package/skills/start/SKILL.md +40 -123
- package/skills/start/references/branch-routing.md +51 -0
- package/skills/start/references/mode-semantics.md +12 -0
- package/skills/start/references/preflight.md +13 -0
- package/skills/start/references/reporting.md +20 -0
- package/skills/start/references/state-seeding.md +44 -0
- package/skills/start/references/workflow-handoff.md +26 -0
- package/skills/status/SKILL.md +17 -61
- package/skills/status/references/gather-contract.md +27 -0
- package/skills/status/references/health-rules.md +27 -0
- package/skills/status/references/output-contract.md +24 -0
- package/skills/status/references/preflight.md +10 -0
- package/skills/status/references/recovery-hints.md +18 -0
- package/skills/ui-sketch/SKILL.md +15 -34
- package/skills/ui-sketch/references/brief-intake.md +10 -0
- package/skills/ui-sketch/references/iteration-handoff.md +5 -0
- package/skills/ui-sketch/references/variant-contract.md +15 -0
- package/skills/verify/SKILL.md +31 -86
- package/skills/verify/references/evidence-workflow.md +39 -0
- package/skills/verify/references/output-contract.md +23 -0
- package/skills/verify/references/preflight.md +11 -0
- package/skills/verify/references/report-handoff.md +35 -0
- package/skills/verify/references/strict-mode.md +12 -0
- package/README.zh.md +0 -160
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
# Fast Execution Contract β Lookup, Verify, Commit
|
|
2
|
+
|
|
3
|
+
## Lightweight Context
|
|
4
|
+
|
|
5
|
+
```bash
|
|
6
|
+
[ -f "CLAUDE.md" ] && cat CLAUDE.md | head -50
|
|
7
|
+
[ -f ".flow/CONTEXT.md" ] && cat .flow/CONTEXT.md | head -30
|
|
8
|
+
```
|
|
9
|
+
|
|
10
|
+
Fast mode may run outside a `.flow/` project. Treat `.flow/CONTEXT.md` as
|
|
11
|
+
optional.
|
|
12
|
+
|
|
13
|
+
## Mandatory Tool Use
|
|
14
|
+
|
|
15
|
+
1. If a library or API is involved: use Context7
|
|
16
|
+
2. Use Grep/Glob to find the relevant code
|
|
17
|
+
3. Read current files before editing
|
|
18
|
+
4. Apply Karpathy's surgical principles
|
|
19
|
+
5. Run validation commands before committing
|
|
20
|
+
|
|
21
|
+
## Commit Requirement
|
|
22
|
+
|
|
23
|
+
Even in fast mode, do not leave changes scattered:
|
|
24
|
+
|
|
25
|
+
```bash
|
|
26
|
+
git add <exact files>
|
|
27
|
+
git commit -m "<type>(<scope>): <summary>"
|
|
28
|
+
```
|
|
29
|
+
|
|
30
|
+
The commit must conform to `atomic-commits.md`.
|
|
31
|
+
|
|
32
|
+
## Output Shape
|
|
33
|
+
|
|
34
|
+
```text
|
|
35
|
+
β Fast execution complete
|
|
36
|
+
|
|
37
|
+
Changes:
|
|
38
|
+
- src/foo.ts (+3 -1)
|
|
39
|
+
- src/foo.test.ts (+15)
|
|
40
|
+
|
|
41
|
+
Verification:
|
|
42
|
+
npm test β
|
|
43
|
+
tsc --noEmit β
|
|
44
|
+
|
|
45
|
+
Commit: abc123f β fix(foo): handle null case
|
|
46
|
+
|
|
47
|
+
Consider the full flow next time?
|
|
48
|
+
/curdx-flow:start <name> "<goal>"
|
|
49
|
+
```
|
|
50
|
+
|
|
51
|
+
## Forbidden
|
|
52
|
+
|
|
53
|
+
- committing without verification
|
|
54
|
+
- letting the change sprawl across unrelated modules
|
|
55
|
+
- writing library APIs from memory
|
|
56
|
+
- skipping the clarification step
|
package/skills/help/SKILL.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: help
|
|
3
|
-
description: Show
|
|
3
|
+
description: Show command detail, workflow guidance, and troubleshooting.
|
|
4
4
|
when_to_use: Use when the user asks how CurdX-Flow works, which command to run, what a workflow does, or how to troubleshoot common issues.
|
|
5
5
|
argument-hint: "[<command-name> | workflow | troubleshoot]"
|
|
6
6
|
disable-model-invocation: true
|
|
@@ -9,152 +9,46 @@ allowed-tools: [Read, Bash]
|
|
|
9
9
|
|
|
10
10
|
# CurdX-Flow Help
|
|
11
11
|
|
|
12
|
-
|
|
12
|
+
Keep this skill focused on menuing and discovery. The canonical quick-overview,
|
|
13
|
+
workflow, and troubleshooting payloads live in:
|
|
13
14
|
|
|
14
|
-
|
|
15
|
+
- `references/dispatch.md`
|
|
16
|
+
- `references/overview.md`
|
|
17
|
+
- `references/workflow.md`
|
|
18
|
+
- `references/troubleshoot.md`
|
|
15
19
|
|
|
16
|
-
|
|
17
|
-
π CurdX-Flow v2 β Claude Code Discipline Layer
|
|
18
|
-
|
|
19
|
-
11 slash commands (explicit control)
|
|
20
|
-
ββββββββββββββββββββββββββββββββββββ
|
|
21
|
-
/curdx-flow:init Initialize .flow/ in the current project
|
|
22
|
-
/curdx-flow:start Create / resume / switch a feature spec
|
|
23
|
-
/curdx-flow:status Show active spec, phase, task progress, recovery hints
|
|
24
|
-
/curdx-flow:spec Write or refresh the spec (--phase, --review, --regenerate)
|
|
25
|
-
/curdx-flow:implement Execute the tasks (auto-routed strategy)
|
|
26
|
-
/curdx-flow:cancel Cancel execution loop safely; optional spec deletion
|
|
27
|
-
/curdx-flow:verify Goal-backward verification β the differentiator
|
|
28
|
-
/curdx-flow:review Two-stage code review (+ --adversarial, --edge-case)
|
|
29
|
-
/curdx-flow:fast Skip the spec β one-shot small task
|
|
30
|
-
/curdx-flow:debug Systematic 4-stage debugging
|
|
31
|
-
/curdx-flow:help This help
|
|
32
|
-
|
|
33
|
-
5 skills (auto-invoked by Claude based on context)
|
|
34
|
-
ββββββββββββββββββββββββββββββββββββ
|
|
35
|
-
epic Decompose a large feature into vertical-slice sub-specs
|
|
36
|
-
browser-qa Real-browser test via chrome-devtools MCP
|
|
37
|
-
ui-sketch Generate UI design variants (via frontend-design skill)
|
|
38
|
-
security-audit OWASP + STRIDE + CVE scan
|
|
39
|
-
brownfield-index Map an unfamiliar / legacy codebase
|
|
40
|
-
|
|
41
|
-
3 MCP servers auto-installed
|
|
42
|
-
ββββββββββββββββββββββββββββββββββββ
|
|
43
|
-
context7 Latest library docs
|
|
44
|
-
sequential-thinking Structured reasoning
|
|
45
|
-
chrome-devtools Browser automation
|
|
46
|
-
|
|
47
|
-
Usage:
|
|
48
|
-
/curdx-flow:help <command> Detail for one command
|
|
49
|
-
/curdx-flow:help workflow Standard workflow walkthrough
|
|
50
|
-
/curdx-flow:help troubleshoot Common problems
|
|
51
|
-
```
|
|
52
|
-
|
|
53
|
-
## `<command-name>` β command detail
|
|
54
|
-
|
|
55
|
-
When the argument matches a slash name β one of the 11 slash commands or one of the 5 auto-invoked skills β read the corresponding body and present it cleanly. The lookup tries the `skills/` layout first and falls back to the legacy `commands/` layout for older installed bundles:
|
|
56
|
-
|
|
57
|
-
```bash
|
|
58
|
-
CMD="$ARGUMENTS"
|
|
59
|
-
[ -z "$CMD" ] && { echo "Usage: /curdx-flow:help <name>"; exit 1; }
|
|
60
|
-
if [ -f "${CLAUDE_PLUGIN_ROOT}/skills/${CMD}/SKILL.md" ]; then
|
|
61
|
-
cat "${CLAUDE_PLUGIN_ROOT}/skills/${CMD}/SKILL.md"
|
|
62
|
-
elif [ -f "${CLAUDE_PLUGIN_ROOT}/commands/${CMD}.md" ]; then
|
|
63
|
-
cat "${CLAUDE_PLUGIN_ROOT}/commands/${CMD}.md"
|
|
64
|
-
else
|
|
65
|
-
echo "Unknown: ${CMD}"
|
|
66
|
-
echo "Workflows: init start status spec implement cancel verify review fast debug help"
|
|
67
|
-
echo "Skills: epic browser-qa ui-sketch security-audit brownfield-index"
|
|
68
|
-
exit 1
|
|
69
|
-
fi
|
|
70
|
-
```
|
|
71
|
-
|
|
72
|
-
If the argument isn't a known slash name, the block above prints the 16 candidates.
|
|
20
|
+
## No Argument β Quick Overview
|
|
73
21
|
|
|
74
|
-
|
|
22
|
+
Render the compact command/skill/MCP summary from `references/overview.md`.
|
|
75
23
|
|
|
76
|
-
|
|
77
|
-
π CurdX-Flow v2 Standard Workflow
|
|
78
|
-
|
|
79
|
-
1. One-time setup (outside Claude Code)
|
|
80
|
-
ββ npx @curdx/flow install --all
|
|
81
|
-
|
|
82
|
-
2. Per project (in Claude Code)
|
|
83
|
-
ββ /curdx-flow:init
|
|
24
|
+
## `<command-name>` β Command Detail
|
|
84
25
|
|
|
85
|
-
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
|
|
89
|
-
ββ (optional) /curdx-flow:spec --review β add multi-dim planning review
|
|
90
|
-
ββ /curdx-flow:implement β execute tasks
|
|
91
|
-
ββ /curdx-flow:verify β goal-backward check
|
|
92
|
-
ββ /curdx-flow:review β code review
|
|
26
|
+
Plugin skills are namespaced. When guiding users toward specialty skills, refer
|
|
27
|
+
to them as `/curdx-flow:<name>`, not bare `/name`. E.g., /curdx-flow:security-audit.
|
|
28
|
+
Canonical specialty paths: /curdx-flow:epic, /curdx-flow:browser-qa,
|
|
29
|
+
/curdx-flow:ui-sketch, /curdx-flow:security-audit, /curdx-flow:brownfield-index.
|
|
93
30
|
|
|
94
|
-
|
|
95
|
-
ββ Say "this feature is too big, break it down" β epic skill auto-invokes
|
|
31
|
+
Use `references/dispatch.md` for:
|
|
96
32
|
|
|
97
|
-
|
|
98
|
-
|
|
33
|
+
- `<command-name>` lookup against the shipped `skills/` layout
|
|
34
|
+
- unknown-command fallback text
|
|
35
|
+
- zero-argument usage guidance for detail mode
|
|
99
36
|
|
|
100
|
-
|
|
101
|
-
ββ /curdx-flow:debug "tests fail intermittently after 3rd run"
|
|
37
|
+
The canonical shipped lookup path is:
|
|
102
38
|
|
|
103
|
-
|
|
104
|
-
|
|
105
|
-
standard Default β spec + gates + review
|
|
106
|
-
enterprise Standard + adversarial + edge-case + security-audit
|
|
39
|
+
```text
|
|
40
|
+
${CLAUDE_PLUGIN_ROOT}/skills/${CMD}/SKILL.md
|
|
107
41
|
```
|
|
108
42
|
|
|
109
|
-
## `
|
|
110
|
-
|
|
111
|
-
```
|
|
112
|
-
π οΈ Common issues
|
|
43
|
+
## `workflow` β Standard Workflow
|
|
113
44
|
|
|
114
|
-
|
|
115
|
-
A: Restart Claude Code. The plugin needs a fresh session to register.
|
|
45
|
+
Render the standard workflow from `references/workflow.md`.
|
|
116
46
|
|
|
117
|
-
|
|
118
|
-
A: Check Node >= 18: node --version
|
|
119
|
-
Check MCPs: claude mcp list
|
|
120
|
-
Health overall: npx @curdx/flow doctor
|
|
47
|
+
## `troubleshoot` β Common Issues
|
|
121
48
|
|
|
122
|
-
|
|
123
|
-
A: v1.1.5+ defaults to offline install (bundled plugin body).
|
|
124
|
-
Force-offline: npx @curdx/flow install --no-deps
|
|
125
|
-
Force-online: npx @curdx/flow install --online
|
|
126
|
-
|
|
127
|
-
Q: claude-mem MCP keeps failing?
|
|
128
|
-
A: It needs bun. Run: npx @curdx/flow doctor
|
|
129
|
-
If doctor reports bun/uv is installed but not on PATH, run:
|
|
130
|
-
npx @curdx/flow doctor --fix
|
|
131
|
-
|
|
132
|
-
Q: /curdx-flow:init says .flow/ already exists?
|
|
133
|
-
A: Use --force, or run /curdx-flow:start directly to begin a new spec in the existing .flow/.
|
|
134
|
-
|
|
135
|
-
Q: Skills don't auto-invoke reliably?
|
|
136
|
-
A: Invoke explicitly β plugin skills are namespaced. E.g., /curdx-flow:security-audit.
|
|
137
|
-
|
|
138
|
-
Q: I want the old v1 commands (research, plan-ceo, partyβ¦).
|
|
139
|
-
A: They're removed in v2. See MIGRATION.md for mappings, or stay on 1.x:
|
|
140
|
-
npm i -g @curdx/flow@^1.1
|
|
141
|
-
|
|
142
|
-
Q: Too many gates blocking progress?
|
|
143
|
-
A: Your spec mode decides gate strictness. Lower via:
|
|
144
|
-
/curdx-flow:start <name> "<goal>" --mode=fast
|
|
145
|
-
|
|
146
|
-
Q: Where are decisions logged?
|
|
147
|
-
A: .flow/STATE.md (D-NN entries). Edit directly β no slash command needed.
|
|
148
|
-
|
|
149
|
-
Q: Stop-hook or execution loop seems stuck?
|
|
150
|
-
A: Run /curdx-flow:status. If state/tasks disagree, run /curdx-flow:cancel, then resume with:
|
|
151
|
-
/curdx-flow:implement --strategy=subagent
|
|
152
|
-
|
|
153
|
-
Q: File a bug / request feature
|
|
154
|
-
A: https://github.com/curdx/curdx-flow/issues
|
|
155
|
-
```
|
|
49
|
+
Render the troubleshooting guide from `references/troubleshoot.md`.
|
|
156
50
|
|
|
157
|
-
## Output
|
|
51
|
+
## Output Principles
|
|
158
52
|
|
|
159
53
|
- Keep it compact. Use tables and lists, not prose.
|
|
160
54
|
- Always point at a concrete next action, not "see the docs".
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
# Help Dispatch β Command Detail Routing
|
|
2
|
+
|
|
3
|
+
When `$ARGUMENTS` is a command or skill name, resolve it from the shipped
|
|
4
|
+
plugin layout:
|
|
5
|
+
|
|
6
|
+
```bash
|
|
7
|
+
CMD="$ARGUMENTS"
|
|
8
|
+
[ -z "$CMD" ] && { echo "Usage: /curdx-flow:help <name>"; exit 1; }
|
|
9
|
+
if [ -f "${CLAUDE_PLUGIN_ROOT}/skills/${CMD}/SKILL.md" ]; then
|
|
10
|
+
cat "${CLAUDE_PLUGIN_ROOT}/skills/${CMD}/SKILL.md"
|
|
11
|
+
else
|
|
12
|
+
echo "Unknown: ${CMD}"
|
|
13
|
+
echo "Workflows: init start status spec implement cancel verify review fast debug help"
|
|
14
|
+
echo "Skills: epic browser-qa ui-sketch security-audit brownfield-index"
|
|
15
|
+
exit 1
|
|
16
|
+
fi
|
|
17
|
+
```
|
|
18
|
+
|
|
19
|
+
This lookup must stay inside `${CLAUDE_PLUGIN_ROOT}/skills/`. Do not fall back
|
|
20
|
+
to any removed `commands/` layout or plugin-cache globbing.
|
|
@@ -0,0 +1,39 @@
|
|
|
1
|
+
# Help Overview β Quick Surface Summary
|
|
2
|
+
|
|
3
|
+
```text
|
|
4
|
+
π CurdX-Flow v2 β Claude Code Discipline Layer
|
|
5
|
+
|
|
6
|
+
11 slash commands (explicit control)
|
|
7
|
+
ββββββββββββββββββββββββββββββββββββ
|
|
8
|
+
/curdx-flow:init Initialize the .flow scaffold for the current repository.
|
|
9
|
+
/curdx-flow:start Create, resume, list, or switch the active feature spec.
|
|
10
|
+
/curdx-flow:status Show active spec health, progress, artifacts, and recovery hints.
|
|
11
|
+
/curdx-flow:spec Generate or refresh research, requirements, design, and tasks for the active spec.
|
|
12
|
+
/curdx-flow:implement Execute active-spec tasks with strategy routing and atomic progress.
|
|
13
|
+
/curdx-flow:cancel Cancel the active execution loop or delete a spec with explicit confirmation.
|
|
14
|
+
/curdx-flow:verify Verify the active spec against code, tests, and browser evidence.
|
|
15
|
+
/curdx-flow:review Run two-stage review with optional adversarial, edge-case, and DevEx passes.
|
|
16
|
+
/curdx-flow:fast Execute a one-shot small task without creating a spec.
|
|
17
|
+
/curdx-flow:debug Debug a bug or failing test with the root-cause workflow.
|
|
18
|
+
/curdx-flow:help Show command detail, workflow guidance, and troubleshooting.
|
|
19
|
+
|
|
20
|
+
5 skills (auto-invoked by Claude based on context)
|
|
21
|
+
ββββββββββββββββββββββββββββββββββββ
|
|
22
|
+
/curdx-flow:epic Decompose a large feature into vertical-slice sub-specs
|
|
23
|
+
/curdx-flow:browser-qa Real-browser test via chrome-devtools MCP
|
|
24
|
+
/curdx-flow:ui-sketch Generate UI design variants (via frontend-design skill)
|
|
25
|
+
/curdx-flow:security-audit OWASP + STRIDE + CVE scan
|
|
26
|
+
/curdx-flow:brownfield-index Map an unfamiliar / inherited codebase
|
|
27
|
+
|
|
28
|
+
3 MCP servers auto-installed
|
|
29
|
+
ββββββββββββββββββββββββββββββββββββ
|
|
30
|
+
context7 Latest library docs
|
|
31
|
+
sequential-thinking Structured reasoning
|
|
32
|
+
chrome-devtools Browser automation
|
|
33
|
+
|
|
34
|
+
Usage:
|
|
35
|
+
/curdx-flow:help <command> Detail for one command
|
|
36
|
+
/curdx-flow:help workflow Standard workflow walkthrough
|
|
37
|
+
/curdx-flow:help troubleshoot Common problems
|
|
38
|
+
/curdx-flow:review --devex Add the DevEx lens to review
|
|
39
|
+
```
|
|
@@ -0,0 +1,47 @@
|
|
|
1
|
+
# Help Troubleshoot β Common Issues
|
|
2
|
+
|
|
3
|
+
```text
|
|
4
|
+
π οΈ Common issues
|
|
5
|
+
|
|
6
|
+
Q: After install, /curdx-flow:* commands are not found.
|
|
7
|
+
A: Restart Claude Code. The plugin needs a fresh session to register.
|
|
8
|
+
|
|
9
|
+
Q: MCP servers not starting?
|
|
10
|
+
A: Check Node >= 18: node --version
|
|
11
|
+
Check MCPs: claude mcp list
|
|
12
|
+
Health overall: npx @curdx/flow doctor
|
|
13
|
+
|
|
14
|
+
Q: GitHub slow / blocked during install?
|
|
15
|
+
A: v1.1.5+ defaults to offline install (bundled plugin body).
|
|
16
|
+
Force-offline: npx @curdx/flow install --no-deps
|
|
17
|
+
Force-online: npx @curdx/flow install --online
|
|
18
|
+
|
|
19
|
+
Q: claude-mem MCP keeps failing?
|
|
20
|
+
A: It needs bun. Run: npx @curdx/flow doctor
|
|
21
|
+
If doctor reports bun/uv is installed but not on PATH, run:
|
|
22
|
+
npx @curdx/flow doctor --fix
|
|
23
|
+
|
|
24
|
+
Q: /curdx-flow:init says .flow/ already exists?
|
|
25
|
+
A: Use --force, or run /curdx-flow:start directly to begin a new spec in the existing .flow/.
|
|
26
|
+
|
|
27
|
+
Q: Skills don't auto-invoke reliably?
|
|
28
|
+
A: Invoke explicitly β plugin skills are namespaced. E.g., /curdx-flow:security-audit.
|
|
29
|
+
|
|
30
|
+
Q: I want the old v1 commands (research, plan-ceo, partyβ¦).
|
|
31
|
+
A: They're removed in v2. Use /curdx-flow:help workflow for the current paths, or stay on 1.x:
|
|
32
|
+
npm i -g @curdx/flow@^1.1
|
|
33
|
+
|
|
34
|
+
Q: Too many gates blocking progress?
|
|
35
|
+
A: Your spec mode decides gate strictness. Lower via:
|
|
36
|
+
/curdx-flow:start <name> "<goal>" --mode=fast
|
|
37
|
+
|
|
38
|
+
Q: Where are decisions logged?
|
|
39
|
+
A: .flow/STATE.md (D-NN entries). Edit directly β no slash command needed.
|
|
40
|
+
|
|
41
|
+
Q: Stop-hook or execution loop seems stuck?
|
|
42
|
+
A: Run /curdx-flow:status. If state/tasks disagree, run /curdx-flow:cancel, then resume with:
|
|
43
|
+
/curdx-flow:implement --strategy=subagent
|
|
44
|
+
|
|
45
|
+
Q: File a bug / request feature
|
|
46
|
+
A: https://github.com/curdx/curdx-flow/issues
|
|
47
|
+
```
|
|
@@ -0,0 +1,37 @@
|
|
|
1
|
+
# Help Workflow β Canonical Main Loop
|
|
2
|
+
|
|
3
|
+
```text
|
|
4
|
+
π CurdX-Flow v2 Standard Workflow
|
|
5
|
+
|
|
6
|
+
1. One-time setup (outside Claude Code)
|
|
7
|
+
ββ npx @curdx/flow install --all
|
|
8
|
+
|
|
9
|
+
2. Per project (in Claude Code)
|
|
10
|
+
ββ /curdx-flow:init
|
|
11
|
+
|
|
12
|
+
3. Per feature β the main loop
|
|
13
|
+
ββ /curdx-flow:start my-feature "one-line goal"
|
|
14
|
+
ββ /curdx-flow:status β optional: see active spec + recovery hints
|
|
15
|
+
ββ /curdx-flow:spec β research β requirements β design β tasks
|
|
16
|
+
ββ (optional) /curdx-flow:spec --review β add multi-dim planning review
|
|
17
|
+
ββ /curdx-flow:implement β execute tasks
|
|
18
|
+
ββ /curdx-flow:verify β goal-backward check
|
|
19
|
+
ββ /curdx-flow:review β code review
|
|
20
|
+
|
|
21
|
+
4. Evidence-backed handoff
|
|
22
|
+
ββ verification-report.md + review-report.md + atomic commits β human PR/release work
|
|
23
|
+
|
|
24
|
+
5. Big feature (breaks into multiple specs)
|
|
25
|
+
ββ Say "this feature is too big, break it down" β epic skill auto-invokes
|
|
26
|
+
|
|
27
|
+
6. One-off task (skip the spec)
|
|
28
|
+
ββ /curdx-flow:fast "rename foo to bar in src/"
|
|
29
|
+
|
|
30
|
+
7. Stuck on a bug
|
|
31
|
+
ββ /curdx-flow:debug "tests fail intermittently after 3rd run"
|
|
32
|
+
|
|
33
|
+
Modes (set via /curdx-flow:start --mode=...)
|
|
34
|
+
fast One-off task paths
|
|
35
|
+
standard Default β spec + gates + review
|
|
36
|
+
enterprise Standard + adversarial + edge-case + devex + security-audit
|
|
37
|
+
```
|