heimdall-agent 1.1.0 → 1.2.0
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 +13 -13
- package/README.pt-BR.md +36 -22
- package/agents/code-sentinel.md +7 -1
- package/agents/modernizer.md +4 -2
- package/agents/orchestrator.md +20 -7
- package/agents/reviewer.md +2 -0
- package/config/agents.json +11 -1
- package/config/mcp.json +1 -1
- package/config/profiles.json +1 -1
- package/config/skills.json +762 -683
- package/docs/SKILLS.md +96 -74
- package/docs/runs/skill-audit/2026-11-12-compare-report.json +1028 -0
- package/docs/runs/skill-audit/2026-11-12-upstream-audit.json +275 -0
- package/doctrine/AGENTS.md +4 -1
- package/lib/catalog-sync.cjs +8 -3
- package/package.json +1 -1
- package/playbooks/01-interactive-grilling-gate.md +14 -10
- package/playbooks/03-adversarial-code-review.md +12 -4
- package/playbooks/05-canonical-plan-template.md +3 -1
- package/setup.mjs +2 -2
- package/skills/antislop-copywriting/SKILL.md +36 -1
- package/skills/brainstorming/SKILL.md +60 -38
- package/skills/codebase-design/DEEPENING.md +37 -0
- package/skills/codebase-design/DESIGN-IT-TWICE.md +44 -0
- package/skills/codebase-design/SKILL.md +114 -0
- package/skills/domain-modeling/ADR-FORMAT.md +47 -0
- package/skills/domain-modeling/GLOSSARY-FORMAT.md +60 -0
- package/skills/domain-modeling/SKILL.md +74 -0
- package/skills/executing-plans/SKILL.md +6 -4
- package/skills/grill-me/SKILL.md +65 -0
- package/skills/handoff/SKILL.md +64 -0
- package/skills/improve-codebase-architecture/HTML-REPORT.md +123 -0
- package/skills/improve-codebase-architecture/SKILL.md +71 -0
- package/skills/owasp-security/reference/config-and-supply-chain.md +346 -344
- package/skills/owasp-security/reference/languages.md +378 -372
- package/skills/owasp-security/reference/owasp-report.md +1144 -1140
- package/skills/owasp-security/reference/review-checklist.md +134 -132
- package/skills/subagent-driven-development/SKILL.md +7 -4
- package/skills/to-spec/SKILL.md +75 -0
- package/skills/to-tickets/SKILL.md +105 -0
- package/skills/wayfinder/SKILL.md +128 -0
|
@@ -0,0 +1,65 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: grill-me
|
|
3
|
+
description: Relentlessly interview the user to stress-test and sharpen a plan, architecture, or design before implementation. Use when planning features, resolving tradeoffs, or when the user invokes /grill-me.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# The Grilling Protocol (Stress-Test & Sharpen Plans)
|
|
7
|
+
|
|
8
|
+
Interview the user relentlessly until you reach an airtight shared understanding. Map the problem space as a **design tree**: every decision branches into the decisions that hang off it.
|
|
9
|
+
|
|
10
|
+
---
|
|
11
|
+
|
|
12
|
+
## 1. The Design Tree Frontier (Round-by-Round)
|
|
13
|
+
|
|
14
|
+
Work the design tree in **rounds**.
|
|
15
|
+
- The **frontier** is every decision whose prerequisites are already settled: the questions you can ask *now* without guessing at answers you haven't heard yet.
|
|
16
|
+
- Ask the whole frontier in one round: number each question and provide your concrete recommendation.
|
|
17
|
+
- **Dependency Rule**: If Question B depends on the choice made in Question A, Question B does NOT belong in this round. It belongs in a *subsequent* round once Question A is resolved.
|
|
18
|
+
|
|
19
|
+
---
|
|
20
|
+
|
|
21
|
+
## 2. The "Yes-to-Approve" Triage Format
|
|
22
|
+
|
|
23
|
+
Always format questions so the user can quickly accept your recommendations with minimal keystrokes (e.g. replying *"1: yes, 2: yes, 3: no do Y"*):
|
|
24
|
+
|
|
25
|
+
```markdown
|
|
26
|
+
❓ **Q1 - <Decision Title>**: <Context, boundary conditions, edge cases, and options>
|
|
27
|
+
|
|
28
|
+
➡️ **Recommended**: <Your recommended answer and justification>
|
|
29
|
+
|
|
30
|
+
---
|
|
31
|
+
|
|
32
|
+
❓ **Q2 - <Decision Title>**: <Context, boundary conditions, edge cases, and options>
|
|
33
|
+
|
|
34
|
+
➡️ **Recommended**: <Your recommended answer and justification>
|
|
35
|
+
```
|
|
36
|
+
|
|
37
|
+
**Rule**: Word each question and recommendation so answering *"yes"* or *"accept"* selects your recommended path.
|
|
38
|
+
|
|
39
|
+
---
|
|
40
|
+
|
|
41
|
+
## 3. Autonomous Fact-Finding Invariant (Zero Lazy Questions)
|
|
42
|
+
|
|
43
|
+
**Finding facts is your job, never the user's.**
|
|
44
|
+
- If a question hinges on a fact from the repository (e.g., existing middleware, schema types, installed package versions, API endpoints, config flags):
|
|
45
|
+
- **Look it up autonomously** using filesystem tools, greps, and doc inspections before asking.
|
|
46
|
+
- Never ask the user for anything you can discover yourself.
|
|
47
|
+
- Only present decisions, requirements, and business trade-offs that cannot be answered by the code.
|
|
48
|
+
|
|
49
|
+
---
|
|
50
|
+
|
|
51
|
+
## 4. ADR & Documentation Integration
|
|
52
|
+
|
|
53
|
+
When grilling uncovers settled architectural decisions for significant or multi-system features:
|
|
54
|
+
- Record each settled decision in an **Architectural Decision Record (ADR)** under `docs/adr/YYYY-MM-DD-<decision>.md` (or the project's designated ADR directory).
|
|
55
|
+
- Keep ADRs compact: Context, Decision, Invariants, Consequences.
|
|
56
|
+
- Maintain consistent domain terminology in the project's domain docs or glossary.
|
|
57
|
+
|
|
58
|
+
---
|
|
59
|
+
|
|
60
|
+
## 5. Exit Criteria
|
|
61
|
+
|
|
62
|
+
The grilling session is complete when:
|
|
63
|
+
1. The decision frontier is empty (all branches visited, zero hidden assumptions).
|
|
64
|
+
2. The user has confirmed the proposed recommendations or made their adjustments.
|
|
65
|
+
3. The agreed scope is ready to be compiled into a specification or plan (`to-spec` / `writing-plans` / `05-canonical-plan-template.md`).
|
|
@@ -0,0 +1,64 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: handoff
|
|
3
|
+
description: Compact the current conversation and session context into an isolated handoff document so a fresh agent or subagent can pick up work without drift.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# The Handoff Protocol
|
|
7
|
+
|
|
8
|
+
When ending a session, switching agent contexts, or spawning a fresh child agent (e.g. via `invoke_subagent`, `herdr`, or `claude --bg`), create a lean, structured handoff document.
|
|
9
|
+
|
|
10
|
+
---
|
|
11
|
+
|
|
12
|
+
## 1. Zero-Duplication & Pointer-First Principle
|
|
13
|
+
|
|
14
|
+
Do **not** dump raw source code, large file bodies, verbose conversational histories, or full plan duplicates into the handoff artifact.
|
|
15
|
+
- **Reference existing artifacts by path or commit hash**:
|
|
16
|
+
- Plan / Spec: `docs/designs/YYYY-MM-DD-<feature>.md`
|
|
17
|
+
- ADRs: `docs/adr/`
|
|
18
|
+
- Git branch & diff: `feature/xyz` (`git diff origin/main..HEAD`)
|
|
19
|
+
- Failing test paths: `tests/integration/...`
|
|
20
|
+
- **Redact secrets**: Strip API keys, session tokens, or sensitive credentials.
|
|
21
|
+
|
|
22
|
+
---
|
|
23
|
+
|
|
24
|
+
## 2. Storage Location
|
|
25
|
+
|
|
26
|
+
Write the handoff file to the operating system's temporary directory to avoid polluting the git working tree:
|
|
27
|
+
- **Windows**: `$env:TEMP\handoff-<feature>-<timestamp>.md` (e.g. `C:\Users\<user>\AppData\Local\Temp\...`)
|
|
28
|
+
- **Linux / macOS**: `/tmp/handoff-<feature>-<timestamp>.md`
|
|
29
|
+
|
|
30
|
+
---
|
|
31
|
+
|
|
32
|
+
## 3. Mandatory Document Structure
|
|
33
|
+
|
|
34
|
+
A handoff document must follow this template:
|
|
35
|
+
|
|
36
|
+
```markdown
|
|
37
|
+
# Session Handoff: <Feature or Task Name>
|
|
38
|
+
|
|
39
|
+
### 1. Status & Blast Radius
|
|
40
|
+
- **Current State**: [WIP / Blocked / Ready for Verification / Awaiting Review]
|
|
41
|
+
- **Target Branch**: `<branch-name>`
|
|
42
|
+
- **Last Verified Commit**: `<short-hash>` (or unstaged changes in working copy)
|
|
43
|
+
|
|
44
|
+
### 2. Settled Decisions & Pointers
|
|
45
|
+
- **Spec / Plan**: [docs/designs/YYYY-MM-DD-feature.md](file:///path/to/spec)
|
|
46
|
+
- **ADR**: [docs/adr/...](file:///path/to/adr)
|
|
47
|
+
- **Decided Invariants**: <1-2 bullet summary of settled boundaries>
|
|
48
|
+
|
|
49
|
+
### 3. Open Frontier & Next Immediate Actions
|
|
50
|
+
1. <Exact first command or test to execute>
|
|
51
|
+
2. <Expected failure or next component to modify>
|
|
52
|
+
|
|
53
|
+
### 4. Suggested Skills for Next Agent
|
|
54
|
+
- `<skill-name-1>`: <Why the next agent should call this skill>
|
|
55
|
+
- `<skill-name-2>`: <Why the next agent should call this skill>
|
|
56
|
+
```
|
|
57
|
+
|
|
58
|
+
---
|
|
59
|
+
|
|
60
|
+
## 4. Seeding the Next Agent
|
|
61
|
+
|
|
62
|
+
- **Antigravity / Subagent**: Launch the subagent with the handoff path or concise summary containing the pointer.
|
|
63
|
+
- **Claude Code CLI**: Run `claude --bg --name "<Task Name>" -- "$(cat <path-to-temp-handoff>)"`. Passing via file keeps the shell from misinterpreting special characters (`$`, backticks).
|
|
64
|
+
- **Herdr Multiplexing**: Seed the target agent pane via `herdr agent prompt <agent> "..."`.
|
|
@@ -0,0 +1,123 @@
|
|
|
1
|
+
# HTML Report Format
|
|
2
|
+
|
|
3
|
+
The architectural review is rendered as a single self-contained HTML file in the OS temp directory. Tailwind and Mermaid both come from CDNs. Mermaid handles graph-shaped diagrams reliably; hand-built divs and inline SVG handle the more editorial visuals (mass diagrams, cross-sections). Mix the two: don't lean on Mermaid for everything, it'll start to look generic.
|
|
4
|
+
|
|
5
|
+
## Scaffold
|
|
6
|
+
|
|
7
|
+
```html
|
|
8
|
+
<!doctype html>
|
|
9
|
+
<html lang="en">
|
|
10
|
+
<head>
|
|
11
|
+
<meta charset="utf-8" />
|
|
12
|
+
<title>Architecture review for {{repo name}}</title>
|
|
13
|
+
<script src="https://cdn.tailwindcss.com"></script>
|
|
14
|
+
<script type="module">
|
|
15
|
+
import mermaid from "https://cdn.jsdelivr.net/npm/mermaid@11/dist/mermaid.esm.min.mjs";
|
|
16
|
+
mermaid.initialize({ startOnLoad: true, theme: "neutral", securityLevel: "loose" });
|
|
17
|
+
</script>
|
|
18
|
+
<style>
|
|
19
|
+
/* small custom layer for things Tailwind doesn't cover cleanly:
|
|
20
|
+
dashed seam lines, hand-drawn-feeling arrow heads, etc. */
|
|
21
|
+
.seam { stroke-dasharray: 4 4; }
|
|
22
|
+
.leak { stroke: #dc2626; }
|
|
23
|
+
.deep { background: linear-gradient(135deg, #0f172a, #1e293b); }
|
|
24
|
+
</style>
|
|
25
|
+
</head>
|
|
26
|
+
<body class="bg-stone-50 text-slate-900 font-sans">
|
|
27
|
+
<main class="max-w-5xl mx-auto px-6 py-12 space-y-12">
|
|
28
|
+
<header>...</header>
|
|
29
|
+
<section id="candidates" class="space-y-10">...</section>
|
|
30
|
+
<section id="top-recommendation">...</section>
|
|
31
|
+
</main>
|
|
32
|
+
</body>
|
|
33
|
+
</html>
|
|
34
|
+
```
|
|
35
|
+
|
|
36
|
+
## Header
|
|
37
|
+
|
|
38
|
+
Repo name, date, and a compact legend: solid box = module, dashed line = seam, red arrow = leakage, thick dark box = deep module. No introduction paragraph. Straight into the candidates.
|
|
39
|
+
|
|
40
|
+
## Candidate card
|
|
41
|
+
|
|
42
|
+
The diagrams carry the weight. Prose is sparse, plain, and uses the glossary terms (from the `/codebase-design` skill) without ceremony.
|
|
43
|
+
|
|
44
|
+
Each candidate is one `<article>`:
|
|
45
|
+
|
|
46
|
+
- **Title**: short, names the deepening (e.g. "Collapse the Order intake pipeline").
|
|
47
|
+
- **Badge row**: recommendation strength (`Strong` = emerald, `Worth exploring` = amber, `Speculative` = slate), plus a tag for the dependency category (`in-process`, `local-substitutable`, `ports & adapters`, `mock`).
|
|
48
|
+
- **Files**: monospaced list, `font-mono text-sm`.
|
|
49
|
+
- **Before / After diagram**: the centrepiece. Two columns, side by side. See patterns below.
|
|
50
|
+
- **Problem**: one sentence. What hurts.
|
|
51
|
+
- **Solution**: one sentence. What changes.
|
|
52
|
+
- **Wins**: bullets, ≤6 words each. e.g. "Tests hit one interface", "Pricing logic stops leaking", "Delete 4 shallow wrappers".
|
|
53
|
+
- **ADR callout** (if applicable): one line in an amber-tinted box.
|
|
54
|
+
|
|
55
|
+
No paragraphs of explanation. If the diagram needs a paragraph to be understood, redraw the diagram.
|
|
56
|
+
|
|
57
|
+
## Diagram patterns
|
|
58
|
+
|
|
59
|
+
Pick the pattern that fits the candidate. Mix them. Don't make every diagram look the same. Variety is part of the point.
|
|
60
|
+
|
|
61
|
+
### Mermaid graph (the workhorse for dependencies / call flow)
|
|
62
|
+
|
|
63
|
+
Use a Mermaid `flowchart` or `graph` when the point is "X calls Y calls Z, and look at the mess." Wrap it in a Tailwind-styled card so it doesn't feel parachuted in. Style with classDef to colour leakage edges red and the deep module dark. Sequence diagrams work well for "before: 6 round-trips; after: 1."
|
|
64
|
+
|
|
65
|
+
```html
|
|
66
|
+
<div class="rounded-lg border border-slate-200 bg-white p-4">
|
|
67
|
+
<pre class="mermaid">
|
|
68
|
+
flowchart LR
|
|
69
|
+
A[OrderHandler] --> B[OrderValidator]
|
|
70
|
+
B --> C[OrderRepo]
|
|
71
|
+
C -.leak.-> D[PricingClient]
|
|
72
|
+
classDef leak stroke:#dc2626,stroke-width:2px;
|
|
73
|
+
class C,D leak
|
|
74
|
+
</pre>
|
|
75
|
+
</div>
|
|
76
|
+
```
|
|
77
|
+
|
|
78
|
+
### Hand-built boxes-and-arrows (when Mermaid's layout fights you)
|
|
79
|
+
|
|
80
|
+
Modules as `<div>`s with borders and labels. Arrows as inline SVG `<line>` or `<path>` elements positioned absolutely over a relative container. Reach for this when you want the "after" diagram to feel like one thick-bordered deep module with greyed-out internals, since Mermaid won't render that with the right weight.
|
|
81
|
+
|
|
82
|
+
### Cross-section (good for layered shallowness)
|
|
83
|
+
|
|
84
|
+
Stack horizontal bands (`h-12 border-l-4`) to show layers a call passes through. Before: 6 thin layers each doing nothing. After: 1 thick band labelled with the consolidated responsibility.
|
|
85
|
+
|
|
86
|
+
### Mass diagram (good for "interface as wide as implementation")
|
|
87
|
+
|
|
88
|
+
Two rectangles per module: one for interface surface area, one for implementation. Before: interface rectangle is nearly as tall as the implementation rectangle (shallow). After: interface rectangle is short, implementation rectangle is tall (deep).
|
|
89
|
+
|
|
90
|
+
### Call-graph collapse
|
|
91
|
+
|
|
92
|
+
Before: a tree of function calls rendered as nested boxes. After: the same tree collapsed into one box, with the now-internal calls shown faded inside it.
|
|
93
|
+
|
|
94
|
+
## Style guidance
|
|
95
|
+
|
|
96
|
+
- Lean editorial, not corporate-dashboard. Generous whitespace. Serif optional for headings (`font-serif` works well with stone/slate).
|
|
97
|
+
- Colour sparingly: one accent (emerald or indigo) plus red for leakage and amber for warnings.
|
|
98
|
+
- Keep diagrams ~320px tall so before/after sits comfortably side by side without scrolling.
|
|
99
|
+
- Use `text-xs uppercase tracking-wider` for module labels inside diagrams, so they read as schematic, not as UI.
|
|
100
|
+
- The only scripts are the Tailwind CDN and the Mermaid ESM import. The report is otherwise static: no app code, no interactivity beyond Mermaid's own rendering.
|
|
101
|
+
|
|
102
|
+
## Top recommendation section
|
|
103
|
+
|
|
104
|
+
One larger card. Candidate name, one sentence on why, anchor link to its card. That's it.
|
|
105
|
+
|
|
106
|
+
## Tone
|
|
107
|
+
|
|
108
|
+
Plain English, concise, but the architectural nouns and verbs come straight from the `/codebase-design` skill. Concision is not an excuse to drift.
|
|
109
|
+
|
|
110
|
+
**Use exactly:** module, interface, implementation, depth, deep, shallow, seam, adapter, leverage, locality.
|
|
111
|
+
|
|
112
|
+
**Never substitute:** component, service, unit (for module) · API, signature (for interface) · boundary (for seam) · layer, wrapper (for module, when you mean module).
|
|
113
|
+
|
|
114
|
+
**Phrasings that fit the style:**
|
|
115
|
+
|
|
116
|
+
- "Order intake module is shallow: interface nearly matches the implementation."
|
|
117
|
+
- "Pricing leaks across the seam."
|
|
118
|
+
- "Deepen: one interface, one place to test."
|
|
119
|
+
- "Two adapters justify the seam: HTTP in prod, in-memory in tests."
|
|
120
|
+
|
|
121
|
+
**Wins bullets** name the gain in glossary terms: *"locality: bugs concentrate in one module"*, *"leverage: one interface, N call sites"*, *"interface shrinks; implementation absorbs the wrappers"*. Don't write *"easier to maintain"* or *"cleaner code"*, because those terms aren't in the glossary and don't earn their place.
|
|
122
|
+
|
|
123
|
+
No hedging, no throat-clearing, no "it's worth noting that…". If a sentence could be a bullet, make it a bullet. If a bullet could be cut, cut it. If a term isn't in the `/codebase-design` glossary, reach for one that is before inventing a new one.
|
|
@@ -0,0 +1,71 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: improve-codebase-architecture
|
|
3
|
+
description: Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
|
|
4
|
+
disable-model-invocation: true
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
# Improve Codebase Architecture
|
|
8
|
+
|
|
9
|
+
Surface architectural friction and propose **deepening opportunities**: refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.
|
|
10
|
+
|
|
11
|
+
This command is _informed_ by the project's domain model and built on a shared design vocabulary:
|
|
12
|
+
|
|
13
|
+
- Call the Skill tool with "codebase-design" for the architecture vocabulary (**module**, **interface**, **depth**, **seam**, **adapter**, **leverage**, **locality**) and its principles (the deletion test, "the interface is the test surface", "one adapter = hypothetical seam, two = real"). Use these terms exactly in every suggestion, and don't drift into "component," "service," "API," or "boundary."
|
|
14
|
+
- The domain language in `GLOSSARY.md` gives names to good seams; ADRs in `docs/adr/` record decisions this command should not re-litigate.
|
|
15
|
+
|
|
16
|
+
## Process
|
|
17
|
+
|
|
18
|
+
### 1. Explore
|
|
19
|
+
|
|
20
|
+
**Scope before you scan: YAGNI.** Deepening a module pays off by making future changes to it easier, so put extra weight on the parts of the codebase that have recently changed. Decide *where* to look before you look:
|
|
21
|
+
|
|
22
|
+
- If the user named a direction (a module, a subsystem, a pain point), take it, and skip the inference below.
|
|
23
|
+
- Otherwise, walk back a good stretch of the commit history (`git log --oneline`) to find the codebase's hot spots, the files and areas that keep coming up, and let those paths pull your attention first. If the changes are scattered with no clear hot spot, widen the net.
|
|
24
|
+
|
|
25
|
+
Read the project's domain glossary (`GLOSSARY.md`) and any ADRs in the area you're touching first.
|
|
26
|
+
|
|
27
|
+
Then spawn a sub-agent with a fresh context window to walk the codebase. Don't follow rigid heuristics; explore organically and note where you experience friction:
|
|
28
|
+
|
|
29
|
+
- Where does understanding one concept require bouncing between many small modules?
|
|
30
|
+
- Where are modules **shallow**, with an interface nearly as complex as the implementation?
|
|
31
|
+
- Where have pure functions been extracted just for testability, but the real bugs hide in how they're called (no **locality**)?
|
|
32
|
+
- Where do tightly-coupled modules leak across their seams?
|
|
33
|
+
- Which parts of the codebase are untested, or hard to test through their current interface?
|
|
34
|
+
|
|
35
|
+
Apply the **deletion test** to anything you suspect is shallow: would deleting it concentrate complexity, or just move it? A "yes, concentrates" is the signal you want.
|
|
36
|
+
|
|
37
|
+
### 2. Present candidates as an HTML report
|
|
38
|
+
|
|
39
|
+
Write a self-contained HTML file to the OS temp directory so nothing lands in the repo. Resolve the temp dir from `$TMPDIR`, falling back to `/tmp` (or `%TEMP%` on Windows), and write to `<tmpdir>/architecture-review-<timestamp>.html` so each run gets a fresh file. Open it for the user (`xdg-open <path>` on Linux, `open <path>` on macOS, `start <path>` on Windows) and tell them the absolute path.
|
|
40
|
+
|
|
41
|
+
The report uses **Tailwind via CDN** for layout and styling, and **Mermaid via CDN** for diagrams where a graph/flow/sequence reliably communicates the structure. Mix Mermaid with hand-crafted CSS/SVG visuals: use Mermaid when relationships are graph-shaped (call graphs, dependencies, sequences), and hand-built divs/SVG when you want something more editorial (mass diagrams, cross-sections, collapse animations). Each candidate gets a **before/after visualisation**. Be visual.
|
|
42
|
+
|
|
43
|
+
For each candidate, render a card with:
|
|
44
|
+
|
|
45
|
+
- **Files**: which files/modules are involved
|
|
46
|
+
- **Problem**: why the current architecture is causing friction
|
|
47
|
+
- **Solution**: plain English description of what would change
|
|
48
|
+
- **Benefits**: explained in terms of locality and leverage, and how tests would improve
|
|
49
|
+
- **Before / After diagram**: side-by-side, custom-drawn, illustrating the shallowness and the deepening
|
|
50
|
+
- **Recommendation strength**: one of `Strong`, `Worth exploring`, `Speculative`, rendered as a badge
|
|
51
|
+
|
|
52
|
+
End the report with a **Top recommendation** section: which candidate you'd tackle first and why.
|
|
53
|
+
|
|
54
|
+
**Use GLOSSARY.md vocabulary for the domain, and the `/codebase-design` vocabulary for the architecture.** If `GLOSSARY.md` defines "Order," talk about "the Order intake module," not "the FooBarHandler," and not "the Order service."
|
|
55
|
+
|
|
56
|
+
**ADR conflicts**: if a candidate contradicts an existing ADR, only surface it when the friction is real enough to warrant revisiting the ADR. Mark it clearly in the card (e.g. a warning callout: _"contradicts ADR-0007, but worth reopening because…"_). Don't list every theoretical refactor an ADR forbids.
|
|
57
|
+
|
|
58
|
+
See [HTML-REPORT.md](HTML-REPORT.md) for the full HTML scaffold, diagram patterns, and styling guidance.
|
|
59
|
+
|
|
60
|
+
Do NOT propose interfaces yet. After the file is written, ask the user: "Which of these would you like to explore?"
|
|
61
|
+
|
|
62
|
+
### 3. Grilling loop
|
|
63
|
+
|
|
64
|
+
Once the user picks a candidate, call the Skill tool with "grilling" to walk the decision tree with them: constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.
|
|
65
|
+
|
|
66
|
+
Side effects happen inline as decisions crystallize; call the Skill tool with "domain-modeling" to keep the domain model current as you go:
|
|
67
|
+
|
|
68
|
+
- **Naming a deepened module after a concept not in `GLOSSARY.md`?** Add the term to `GLOSSARY.md`. Create the file lazily if it doesn't exist.
|
|
69
|
+
- **Sharpening a fuzzy term during the conversation?** Update `GLOSSARY.md` right there.
|
|
70
|
+
- **User rejects the candidate with a load-bearing reason?** Offer an ADR, framed as: _"Want me to record this as an ADR so future architecture reviews don't re-suggest it?"_ Only offer when the reason would actually be needed by a future explorer to avoid re-suggesting the same thing; skip ephemeral reasons ("not worth it right now") and self-evident ones.
|
|
71
|
+
- **Want to explore alternative interfaces for the deepened module?** Call the Skill tool with "codebase-design" and use its design-it-twice parallel sub-agent pattern.
|