haac-aikit 0.11.0 → 0.11.1

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 CHANGED
@@ -4,89 +4,31 @@
4
4
  [![GitHub](https://img.shields.io/badge/github-Hamad--Center%2Fhaac--aikit-blue?logo=github)](https://github.com/Hamad-Center/haac-aikit)
5
5
  [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
6
6
 
7
- One command drops a working AI-coding setup into any repo rules, skills, safety hooks, subagents, MCP stub, CI templates for Claude Code, Cursor, Copilot, Windsurf, Aider, Gemini CLI, and Codex.
8
-
9
- ## Quickstart
7
+ **Docs that update themselves.** A cross-tool AI-coding kit (Claude Code, Cursor, Copilot, Windsurf, Aider, Gemini, Codex) that drops opinionated rules + skills + safety hooks into any repo. Headline feature: two new skills that maintain your project's HTML documentation and decision log as the code changes.
10
8
 
11
9
  ```bash
12
10
  npx haac-aikit
13
11
  ```
14
12
 
15
- 30-second wizard, writes a `.aikitrc.json` you can commit. Re-run anytime with `aikit sync`.
16
-
17
- For CI or scripts:
18
-
19
- ```bash
20
- npx haac-aikit --yes --tools=claude,cursor,copilot --preset=standard
21
- ```
22
-
23
- ## What you get
24
-
25
- ### Minimal scope
26
-
27
- | File | Purpose |
28
- |---|---|
29
- | `AGENTS.md` | Canonical rules — your edits outside BEGIN/END markers are never touched |
30
- | `CLAUDE.md` | Five-line shim that imports `@AGENTS.md` |
31
- | `.cursor/rules/000-base.mdc` | Dialect-translated MDC (not a generic copy) |
32
- | Per-tool shims | Copilot, Gemini, Windsurf, Aider |
33
- | `.mcp.json` | MCP stub: filesystem, memory, fetch |
34
- | `.claude/settings.json` | Hardened permissions: deny list for secrets and destructive commands |
35
-
36
- ### Standard scope adds
37
-
38
- - **18 process skills** in `.claude/skills/` — TDD, brainstorming, debugging, git workflows, and more. Bodies load on demand, ~100 tokens at rest.
39
- - **14 agents** in `.claude/agents/` — planner, reviewer, debugger, pr-describer, and more.
40
- - **Safety hooks** — blocks force-push to main, secret commits, `rm -rf`, reads of `.env*` / `.ssh*` / `.aws*`. Fires before the tool call, doesn't rely on the model cooperating.
41
- - **Rule observability hooks** — logs which rules load and which get violated, feeds `aikit doctor --rules`.
42
- - **`/docs` skill** — keeps a small HTML documentation tree at `docs/` current. Section-bounded updates so the agent reads/edits one block, not the whole file.
43
- - **`/decide` skill (opt-in)** — generates one rich HTML tradeoff page per decision under `docs/decisions/`. Plain-language pros/cons, recommended option marked, written so a non-engineer stakeholder can scan it.
44
- - CI workflows: gitleaks, standard CI, optional `@claude` PR responder.
45
-
46
- ### Everything scope adds
47
-
48
- Dev container, OTel exporter, plugin wrapper, auto-sync CI, shape-specific agents (frontend / backend / mobile).
49
-
50
- ## What makes it different
13
+ ## The two headline skills (v0.11)
51
14
 
52
- **Rule observability.** Telemetry hooks tell you which rules fire, which get violated, and which are dead weight. `aikit doctor --rules` shows the buckets; `aikit report` formats them for a PR comment. [docs/observability.md](docs/observability.md)
15
+ - **`/docs`** keeps a living HTML documentation tree at `docs/` current. The agent reads only the section it needs (via marker-bounded blocks), proposes the edit in chat, writes after you confirm. Your README stops going stale.
16
+ - **`/decide`** — generates one rich HTML tradeoff page per architectural choice, saved to `docs/decisions/YYYY-MM-DD-<slug>.html`. Options as cards, pros/cons as colored dots, technical bit explained in plain language. A permanent decision log accumulates.
53
17
 
54
- **Dialect translation.** One canonical `AGENTS.md`, reformatted per tool proper MDC frontmatter for Cursor, emphasis tokens for Claude, imperative phrasing for Aider. You stop maintaining four copies of the same rules. [docs/dialects.md](docs/dialects.md)
18
+ Built on Thariq Shihipar's [Unreasonable Effectiveness of HTML for Claude Code](https://thariqs.github.io/html-effectiveness/) generating HTML instead of markdown gives you scannable, interactive output. We took the insight and built the workflows that compound the longest.
55
19
 
56
- **Learn from your PR history.** `aikit learn --limit=30` mines merged PR review comments for repeated corrections and proposes them as new rules. No ML — just regex, a stopword list, and Jaccard similarity. → [docs/learn.md](docs/learn.md)
20
+ ## What else you get
57
21
 
58
- ## Why the HTML side stays small (one starter, not 20 templates)
22
+ Beyond `/docs` and `/decide`, a `standard` install drops in:
59
23
 
60
- An earlier version of this kit shipped 20 HTML templates PR reviews, slide decks, design systems, prototype animations, feature-flag editors, prompt tuners. Beautiful catalog. **We deleted it.** Here's the honest reason:
24
+ - **Cross-tool rules** one canonical `AGENTS.md`, dialect-translated per tool (proper MDC for Cursor, emphasis tokens for Claude, imperative phrasing for Aider). Stop maintaining four copies.
25
+ - **Safety hooks** — block force-push to main, secret commits, `rm -rf`, reads of `.env*` / `.ssh*` / `.aws*`. Fires before the tool call.
26
+ - **Rule observability** — telemetry tells you which rules fire, get violated, or are dead weight. `aikit doctor --rules` shows the buckets.
27
+ - **Learn from PR history** — `aikit learn --limit=30` mines merged PR reviews for repeated corrections, proposes them as new rules.
28
+ - **18 process skills + 14 agents** — TDD, brainstorming, debugging, planner, reviewer, debugger, pr-describer, more.
29
+ - **CI templates** — gitleaks, standard CI, optional `@claude` PR responder.
61
30
 
62
- - **Developers don't browse a 20-template catalog.** They open the skill, see the wall of patterns, scroll past it, and write whatever HTML they were going to write anyway. Most of those templates were never reached for in practice. A library nobody borrows from is just shelves.
63
- - **A 205-line always-on skill is expensive to keep around.** Every agent invocation paid for that context, even when the user wasn't generating HTML at all. We were taxing every conversation to support a rare action.
64
- - **Two real jobs, not twenty edge cases.** When we asked what people actually needed HTML for, two patterns kept surfacing: (1) **living project docs** they could share for handover, and (2) **tradeoff pages** when there's a decision to make. Everything else was a curated showcase, not a tool.
65
-
66
- So `/html` got split into two focused skills:
67
-
68
- - **`/docs`** — always-on, ~80-line skill, one starter HTML template. Maintains an HTML doc tree at `docs/` with section-bounded surgical updates.
69
- - **`/decide`** — opt-in tier2, ~50-line skill, one rich tradeoff template. Each call writes a new dated file under `docs/decisions/`.
70
-
71
- Both lean on the marker engine for section-level reads/writes (HTML stays cheap because the agent never reloads the whole file). The skill files together are smaller than the old single skill alone. **Less to read, less to maintain, more actual usage.**
72
-
73
- If you want the deleted templates back, fork the previous release (`git checkout v0.10.0 -- catalog/templates/html-artifacts/`) — they're forks of [github.com/ThariqS/html-effectiveness](https://github.com/ThariqS/html-effectiveness) and still useful as reference material.
74
-
75
- ## Commands
76
-
77
- ```
78
- aikit interactive wizard
79
- aikit sync regenerate from .aikitrc.json (idempotent)
80
- aikit update pull latest templates, show diff, prompt
81
- aikit diff show drift between current state and a fresh sync
82
- aikit add <item> add a single skill, command, agent, or hook
83
- aikit list show installed items + catalog availability
84
- aikit doctor schema, triggers, broken-link checks
85
- aikit doctor --rules rule observability buckets
86
- aikit report Markdown adherence summary
87
- aikit report --format=json same data, structured for CI
88
- aikit learn --limit=30 propose rules from your PR review history
89
- ```
31
+ Run `npx haac-aikit` for the wizard, or `npx haac-aikit --yes --tools=claude --preset=standard` for headless / CI.
90
32
 
91
33
  ## How it compares
92
34
 
@@ -97,18 +39,28 @@ aikit learn --limit=30 propose rules from your PR review history
97
39
  | Rule observability | yes | no | no | no |
98
40
  | Dialect translation | yes | no | no | no |
99
41
  | Learn from PR history | yes | no | no | no |
42
+ | Living HTML docs (`/docs`) + decision log (`/decide`) | yes | no | no | no |
100
43
  | Idempotent BEGIN/END markers | yes | no | `.bak` backups | no |
101
44
 
102
- ## Status
103
-
104
- 0.11.0. Holding 1.0 until at least three external teams have used the observability loop on real PRs. Until then, expect breaking changes between minor versions.
45
+ ## Commands
105
46
 
106
- Looking for teams to try it — feedback shapes 1.0. Comment on [issue #1](https://github.com/Hamad-Center/haac-aikit/issues/1).
47
+ ```
48
+ aikit interactive wizard
49
+ aikit sync regenerate from .aikitrc.json
50
+ aikit update pull latest templates, show diff
51
+ aikit add <item> add a single skill / command / agent / hook
52
+ aikit list show installed items + catalog
53
+ aikit doctor [--rules] sanity / observability check
54
+ aikit report [--format=...] adherence summary (markdown or json)
55
+ aikit learn --limit=30 propose rules from your PR review history
56
+ ```
107
57
 
108
- ## Contributing
58
+ ## Status & links
109
59
 
110
- Issues and PRs welcome at [github.com/Hamad-Center/haac-aikit](https://github.com/Hamad-Center/haac-aikit).
60
+ **0.11.0** holding 1.0 until at least three external teams have used the observability loop on real PRs. Expect breaking changes between minor versions until then.
111
61
 
112
- ## License
62
+ - Site: <https://hamad-center.github.io/haac-aikit/>
63
+ - Discussion / try-it sign-up: [issue #1](https://github.com/Hamad-Center/haac-aikit/issues/1)
64
+ - Why we cut the old 20-template HTML skill: [the landing page](https://hamad-center.github.io/haac-aikit/) explains it — short version: developers don't browse a 20-template menu, two real workflows do 100% of the job. Recover the deleted templates with `git checkout v0.10.0 -- catalog/templates/html-artifacts/` if you want them.
113
65
 
114
66
  MIT. See [ATTRIBUTIONS.md](ATTRIBUTIONS.md).
@@ -1,6 +1,20 @@
1
1
  {
2
2
  "version": 1,
3
3
  "releases": [
4
+ {
5
+ "version": "0.11.1",
6
+ "date": "2026-05-13",
7
+ "headline": "Docs-only patch: punchier landing + trimmed README",
8
+ "highlights": [
9
+ "Landing: new hero \"Docs that update themselves\" + without/with comparison block",
10
+ "Landing: Thariq Shihipar's HTML article elevated to a pull-quote attribution",
11
+ "README: 114 → 66 lines, /docs + /decide pulled to top as headline feature",
12
+ "No code changes — same surface as 0.11.0"
13
+ ],
14
+ "links": {
15
+ "changelog": "https://github.com/Hamad-Center/haac-aikit/blob/main/CHANGELOG.md#0111---2026-05-13"
16
+ }
17
+ },
4
18
  {
5
19
  "version": "0.11.0",
6
20
  "date": "2026-05-13",
package/dist/cli.mjs CHANGED
@@ -3620,7 +3620,7 @@ var _internal = {
3620
3620
  };
3621
3621
 
3622
3622
  // src/cli.ts
3623
- var VERSION = "0.11.0";
3623
+ var VERSION = "0.11.1";
3624
3624
  var HELP = `
3625
3625
  haac-aikit \u2014 the batteries-included AI-agentic-coding kit
3626
3626
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "haac-aikit",
3
- "version": "0.11.0",
3
+ "version": "0.11.1",
4
4
  "description": "The batteries-included AI-agentic-coding kit. One command drops a complete, opinionated, cross-tool setup into any repo.",
5
5
  "type": "module",
6
6
  "bin": {