create-religion 0.5.0 → 1.1.0
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 +17 -1
- package/dist/bin/religion.js +90 -49
- package/dist/lib/args.js +108 -0
- package/dist/lib/dashboard.js +945 -83
- package/dist/lib/doctor.js +5 -1
- package/dist/lib/install.js +222 -12
- package/dist/lib/merge.js +23 -0
- package/dist/lib/state.js +168 -11
- package/package.json +2 -2
- package/template/.agents/skills/scout/SKILL.md +82 -0
- package/template/.agents/skills/setup/SKILL.md +117 -12
- package/template/.agents/skills/setup/reference/drafted-plans.md +133 -0
- package/template/.agents/skills/status/SKILL.md +1 -1
- package/template/.claude/hooks/write-handoff.mjs +11 -2
- package/template/.claude/skills/scout/SKILL.md +82 -0
- package/template/.claude/skills/setup/SKILL.md +117 -12
- package/template/.claude/skills/setup/reference/drafted-plans.md +133 -0
- package/template/.claude/skills/status/SKILL.md +1 -1
- package/template/AGENTS.md +1 -0
|
@@ -0,0 +1,133 @@
|
|
|
1
|
+
# Drafted plans - the target shape
|
|
2
|
+
|
|
3
|
+
What /setup writes into `religion/project-plan.md` and `religion/build-plan.md` when it
|
|
4
|
+
surveys a project that already exists. This is the shape to aim at, and the standard the
|
|
5
|
+
draft is judged against before it is shown.
|
|
6
|
+
|
|
7
|
+
A drafted plan is a **reading of the repository offered for correction**, not a finished
|
|
8
|
+
plan. The person reviewing it knows why the project exists; the code does not. The draft's
|
|
9
|
+
job is to save them the typing they would resent, and to be obviously wrong in the places
|
|
10
|
+
it guessed, so they correct it instead of trusting it.
|
|
11
|
+
|
|
12
|
+
## Found, inferred, and missing
|
|
13
|
+
|
|
14
|
+
Three states, and conflating them is the failure this whole reference exists to prevent.
|
|
15
|
+
|
|
16
|
+
| State | Meaning | How it is written |
|
|
17
|
+
| --- | --- | --- |
|
|
18
|
+
| Found | read directly out of the repository | plainly, as a statement |
|
|
19
|
+
| Inferred | concluded from what was read | the claim, then `(inferred)` |
|
|
20
|
+
| Missing | the repository does not answer it | a question addressed to the reader |
|
|
21
|
+
|
|
22
|
+
The code says what was built and never why. Every sentence about intent, audience, or
|
|
23
|
+
motivation is inferred at best, so mark it. A section with no evidence behind it is left as
|
|
24
|
+
a question:
|
|
25
|
+
|
|
26
|
+
## 1. Problem
|
|
27
|
+
|
|
28
|
+
> Not found in the repository. What problem does this solve, and what is broken or
|
|
29
|
+
> missing without it?
|
|
30
|
+
|
|
31
|
+
That is a better draft than a confident paragraph assembled from a README's opening line.
|
|
32
|
+
An unmarked guess is worse than a blank, because nothing downstream will question it.
|
|
33
|
+
|
|
34
|
+
## The project plan, section by section
|
|
35
|
+
|
|
36
|
+
Sections 1 through 5 are required and /overview validates that they are answered
|
|
37
|
+
rather than left as the prompts they ship with. Sections 6 through 8 are optional and are
|
|
38
|
+
deleted rather than filled with "not applicable".
|
|
39
|
+
|
|
40
|
+
### 1. Problem
|
|
41
|
+
|
|
42
|
+
- **Derived from:** the README's opening, any `docs/` introduction, the repository
|
|
43
|
+
description, and the earliest commits, which are often the clearest statement of intent
|
|
44
|
+
the project ever made.
|
|
45
|
+
- **Aim for:** what is broken or missing without this, in a few sentences.
|
|
46
|
+
- **Do not:** restate what the software does. "A CLI that renders markdown" is section 3.
|
|
47
|
+
|
|
48
|
+
### 2. Users
|
|
49
|
+
|
|
50
|
+
- **Derived from:** authentication and authorization code, roles and permissions, distinct
|
|
51
|
+
entry points, and any onboarding or pricing copy.
|
|
52
|
+
- **Aim for:** the kinds of user the code actually distinguishes, and what each needs. Note
|
|
53
|
+
access tiers where they exist, such as anonymous against signed in.
|
|
54
|
+
- **Do not:** invent personas. A project with one unauthenticated entry point has one kind
|
|
55
|
+
of user, and saying so is a finding.
|
|
56
|
+
|
|
57
|
+
### 3. Features
|
|
58
|
+
|
|
59
|
+
- **Derived from:** entry points, routes, commands, exported surface, and the directory
|
|
60
|
+
layout.
|
|
61
|
+
- **Aim for:** one line each, high level, describing what the software already does. This
|
|
62
|
+
is identity, not a queue.
|
|
63
|
+
- **Do not:** list every function, or promote a helper into a feature.
|
|
64
|
+
|
|
65
|
+
### 4. Data
|
|
66
|
+
|
|
67
|
+
- **Derived from:** schema and migration files, type and model definitions, serialization
|
|
68
|
+
code, and the shapes written to disk or across the wire.
|
|
69
|
+
- **Aim for:** the entities, roughly what they hold, and how they relate, in enough detail
|
|
70
|
+
that /overview can turn it into a concrete model. A project with no database still
|
|
71
|
+
has one: the shapes it reads and emits.
|
|
72
|
+
- **Do not:** copy the schema verbatim. Distil it.
|
|
73
|
+
|
|
74
|
+
### 5. Tech
|
|
75
|
+
|
|
76
|
+
- **Derived from:** the dependency manifest, lockfile, language version files, build and
|
|
77
|
+
task configuration, and continuous integration workflows.
|
|
78
|
+
- **Aim for:** the stack, one line each on what it is for here.
|
|
79
|
+
- **Do not:** list transitive dependencies, or record a version the manifest does not pin.
|
|
80
|
+
|
|
81
|
+
### 6. Monetization, 7. UI and UX, 8. Deployment
|
|
82
|
+
|
|
83
|
+
Optional. Draft one only where the repository actually answers it: billing or payment code
|
|
84
|
+
for 6, routes and design tokens for 7, deployment configuration, container files, or host
|
|
85
|
+
workflows for 8. Delete the heading otherwise rather than leaving a prompt behind.
|
|
86
|
+
|
|
87
|
+
## The build plan
|
|
88
|
+
|
|
89
|
+
An existing project's build plan starts from reality: what shipped is checked, so numbering
|
|
90
|
+
and history are honest from the first day.
|
|
91
|
+
|
|
92
|
+
### The item line
|
|
93
|
+
|
|
94
|
+
- [x] 1. **Skill submission** - upload a package and save its metadata
|
|
95
|
+
- [ ] 2. **Validation result** - run checks and show pass or fail per submission
|
|
96
|
+
|
|
97
|
+
This exact form is load-bearing. The loop parses these lines to count progress, to find the
|
|
98
|
+
first unchecked item, and to tick items off at completion. A drafted plan that does not
|
|
99
|
+
match it leaves the project unable to track its own work.
|
|
100
|
+
|
|
101
|
+
- checkbox, number, full stop
|
|
102
|
+
- title in bold
|
|
103
|
+
- ` - ` then one line on what it delivers
|
|
104
|
+
- all of it under the `## Plan` heading
|
|
105
|
+
|
|
106
|
+
### What goes in it
|
|
107
|
+
|
|
108
|
+
- **Shipped work, checked.** One item per feature the survey found, in the order the
|
|
109
|
+
history suggests they were built. This is where most of a mature project's plan comes
|
|
110
|
+
from.
|
|
111
|
+
- **Unshipped work, unchecked**, only where the reader names it or the repository states it
|
|
112
|
+
outright, in a roadmap file or issue text.
|
|
113
|
+
- **Nothing else.** Do not queue refactors, cleanups, or fixes that the survey noticed.
|
|
114
|
+
Those have their own paths, and a plan that opens with someone else's cleanup reads as an
|
|
115
|
+
agent's backlog rather than the reader's.
|
|
116
|
+
|
|
117
|
+
Feature-sized outcomes only: not "Database", not "Make it faster", and not one line holding
|
|
118
|
+
three unrelated capabilities.
|
|
119
|
+
|
|
120
|
+
## Before it is shown
|
|
121
|
+
|
|
122
|
+
/overview validates the plans and will reject a draft that fails these, so check
|
|
123
|
+
them here rather than one stage later:
|
|
124
|
+
|
|
125
|
+
- sections 1 through 5 answered, or explicitly left as questions, and never left as the
|
|
126
|
+
shipped prompts
|
|
127
|
+
- the build plan is a checkbox list under `## Plan`, matching the item line above
|
|
128
|
+
- every item is a feature-sized outcome
|
|
129
|
+
- nothing in the build plan describes a bug or a review pass rather than a feature
|
|
130
|
+
- every inferred claim carries its marker, and every gap reads as a question
|
|
131
|
+
|
|
132
|
+
Then stop and show both drafts in full. The plans belong to the reader: propose, show the
|
|
133
|
+
exact content, and wait.
|
|
@@ -47,7 +47,7 @@ Say "up to date" rather than inventing a warning when there is nothing wrong.
|
|
|
47
47
|
| All steps ticked, not verified | /check |
|
|
48
48
|
| Verified, findings blocking | /audit, or repair via /implement |
|
|
49
49
|
| Verified, nothing blocking | /complete |
|
|
50
|
-
| Plan complete | Add to the plan, or /release |
|
|
50
|
+
| Plan complete | Add to the plan, with /scout for ideas, or /release |
|
|
51
51
|
|
|
52
52
|
When two apply, take the one further along: finishing beats starting.
|
|
53
53
|
|
package/template/AGENTS.md
CHANGED
|
@@ -72,6 +72,7 @@ and follow directly.
|
|
|
72
72
|
- `refactor` - simplify existing code in one behaviour-preserving campaign at a time
|
|
73
73
|
- `release` - prepare deployment readiness for Railway, Render, or Vercel
|
|
74
74
|
- `rollback` - plan a guarded reversal of completed work, preserving its history
|
|
75
|
+
- `scout` - propose new features grounded in what the codebase already has
|
|
75
76
|
- `setup` - tune the installation to this project, greenfield or existing
|
|
76
77
|
- `spike` - answer one feasibility question with throwaway code, then delete it
|
|
77
78
|
- `status` - say where the work stands and what to do next
|