@hopla/claude-setup 1.1.2 → 1.1.4
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/README.md +30 -0
- package/files/commands/hopla-plan-feature.md +9 -7
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -47,6 +47,36 @@ CLAUDE.md (project root) ← Project-specific rules (created with /hopla-init-
|
|
|
47
47
|
|
|
48
48
|
---
|
|
49
49
|
|
|
50
|
+
## The Agentic Coding Framework
|
|
51
|
+
|
|
52
|
+
This system is built on two core concepts from the Agentic Coding Course:
|
|
53
|
+
|
|
54
|
+
### AI Layer — What guides the agent
|
|
55
|
+
|
|
56
|
+
| Pillar | What it is | Where it lives |
|
|
57
|
+
|--------|-----------|----------------|
|
|
58
|
+
| **Global Rules** | Always-loaded context: language, git flow, tech defaults, autonomy rules | `~/.claude/CLAUDE.md` |
|
|
59
|
+
| **On-Demand Context** | Task-specific guides loaded when needed (e.g. "how to add an API endpoint") | `.agents/guides/*.md` |
|
|
60
|
+
| **Commands** | Reusable processes that tell the agent *how* to work | `~/.claude/commands/hopla-*.md` |
|
|
61
|
+
|
|
62
|
+
The key insight: **commands inject on-demand context deterministically** — when you run `/hopla-plan-feature`, it automatically reads the relevant guide from `.agents/guides/` before planning.
|
|
63
|
+
|
|
64
|
+
### PIV Loop — How you work
|
|
65
|
+
|
|
66
|
+
```
|
|
67
|
+
Plan → Implement → Validate → (repeat)
|
|
68
|
+
```
|
|
69
|
+
|
|
70
|
+
- **Plan** (`/hopla-plan-feature`) — Research the codebase, design the approach, create a structured plan
|
|
71
|
+
- **Implement** (`/hopla-execute`) — Delegate coding to the AI, trust but verify at each task
|
|
72
|
+
- **Validate** — AI runs lint → types → tests → integration; human reviews the result
|
|
73
|
+
|
|
74
|
+
### System Evolution
|
|
75
|
+
|
|
76
|
+
After each PIV loop, run `/hopla-execution-report` + `/hopla-system-review` to find process improvements. Don't just fix bugs — fix the system that allowed them.
|
|
77
|
+
|
|
78
|
+
---
|
|
79
|
+
|
|
50
80
|
## What Gets Installed
|
|
51
81
|
|
|
52
82
|
**`~/.claude/CLAUDE.md`** — Global rules applied to every Claude Code session.
|
|
@@ -84,16 +84,18 @@ Key files the executing agent must read before starting:
|
|
|
84
84
|
|
|
85
85
|
## Implementation Tasks
|
|
86
86
|
|
|
87
|
+
> All fields are required. Use `N/A` if a field does not apply — never leave a field blank.
|
|
88
|
+
|
|
87
89
|
### Task 1: [Action verb + what]
|
|
88
|
-
- **Action:**
|
|
89
|
-
- **File:** `[exact file path]`
|
|
90
|
-
- **Pattern:**
|
|
91
|
-
- **Details:** [
|
|
92
|
-
- **Gotcha:** [Known pitfall or constraint
|
|
93
|
-
- **Validate:** [
|
|
90
|
+
- **Action:** create | modify | delete
|
|
91
|
+
- **File:** `[exact file path — no vague references like "the component"]`
|
|
92
|
+
- **Pattern:** `[exact reference file to follow]` — or `N/A` if no existing pattern
|
|
93
|
+
- **Details:** [Step-by-step description of what to implement]
|
|
94
|
+
- **Gotcha:** [Known pitfall or constraint] — or `N/A`
|
|
95
|
+
- **Validate:** [Exact command or check to confirm this task is done correctly]
|
|
94
96
|
|
|
95
97
|
### Task 2: [Action verb + what]
|
|
96
|
-
[Same structure]
|
|
98
|
+
[Same structure — all 6 fields required]
|
|
97
99
|
|
|
98
100
|
[Continue for all tasks...]
|
|
99
101
|
|