ai-engineering-loop 1.14.0 → 1.15.0
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/.agents/{workflows/ai-engineering-loop.md → skills/ai-engineering-loop/SKILL.md} +8 -6
- package/.agents/skills/ai-engineering-loop/references/loop-hosts.md +44 -0
- package/.claude/skills/ai-engineering-loop/SKILL.md +9 -10
- package/.claude/skills/ai-engineering-loop/references/loop-hosts.md +44 -0
- package/CHANGELOG.md +47 -0
- package/README.md +52 -6
- package/adapters/dot/README.md +1 -1
- package/bin/ai-engineering-loop.js +296 -11
- package/core/grill-policy.md +1 -1
- package/core/runtime-safety.md +2 -1
- package/lib/auto-update.js +3 -1
- package/lib/cli-args.js +11 -0
- package/lib/doctor.js +4 -15
- package/lib/host-skill-build.js +15 -15
- package/lib/hosts/agent-formats.js +135 -0
- package/lib/hosts/commands.js +126 -0
- package/lib/hosts/detect.js +56 -0
- package/lib/hosts/doctor.js +76 -0
- package/lib/hosts/redetect.js +60 -0
- package/lib/hosts/registry.js +271 -0
- package/lib/hosts/table.js +35 -0
- package/lib/run-abandon.js +116 -0
- package/lib/sync-hosts.js +155 -112
- package/package.json +2 -3
- package/.agents/devil-advocate.md +0 -79
- package/.agents/judge.md +0 -58
- package/.claude/commands/ai-engineering-loop.md +0 -11
- package/.gemini/skills/ai-engineering-loop/SKILL.md +0 -61
- package/.gemini/skills/animate/RECIPES.md +0 -324
- package/.gemini/skills/animate/SKILL.md +0 -207
- package/.gemini/skills/animate-expo/RECIPES.md +0 -385
- package/.gemini/skills/animate-expo/SKILL.md +0 -263
- package/.gemini/skills/animation-vocabulary/SKILL.md +0 -181
- package/.gemini/skills/apple-design/SKILL.md +0 -290
- package/.gemini/skills/ask-sonner/API.md +0 -64
- package/.gemini/skills/ask-sonner/SKILL.md +0 -88
- package/.gemini/skills/backend-development/SKILL.md +0 -272
- package/.gemini/skills/backend-development/references/api-design-guidelines.md +0 -95
- package/.gemini/skills/backend-development/references/query-and-database-best-practices.md +0 -53
- package/.gemini/skills/backend-development/references/security-checklist.md +0 -60
- package/.gemini/skills/emil-design-eng/SKILL.md +0 -674
- package/.gemini/skills/find-animation-opportunities/SKILL.md +0 -140
- package/.gemini/skills/improve-animations/AUDIT.md +0 -115
- package/.gemini/skills/improve-animations/PLAN-TEMPLATE.md +0 -73
- package/.gemini/skills/improve-animations/SKILL.md +0 -109
- package/.gemini/skills/mobile-native/SKILL.md +0 -311
- package/.gemini/skills/pick-ui-library/SKILL.md +0 -85
- package/.gemini/skills/prototype/PICKER.md +0 -197
- package/.gemini/skills/prototype/SKILL.md +0 -98
- package/.gemini/skills/review-animations/SKILL.md +0 -120
- package/.gemini/skills/review-animations/STANDARDS.md +0 -187
- package/.gemini/skills/write-swift/SKILL.md +0 -396
- package/.grok/commands/ai-engineering-loop.md +0 -11
- package/.grok/skills/ai-engineering-loop/SKILL.md +0 -62
- package/.grok/skills/ai-engineering-loop/references/loop-commands.md +0 -20
- package/.grok/skills/ai-engineering-loop/references/loop-deliver.md +0 -8
- package/.grok/skills/ai-engineering-loop/references/loop-goal.md +0 -10
- package/.grok/skills/ai-engineering-loop/references/loop-maker.md +0 -8
- package/.grok/skills/ai-engineering-loop/references/loop-review.md +0 -18
- package/.grok/skills/ai-engineering-loop/references/loop-risky.md +0 -9
- package/.grok/skills/ai-engineering-loop/references/loop-verify.md +0 -20
- package/.grok/skills/animate/RECIPES.md +0 -324
- package/.grok/skills/animate/SKILL.md +0 -207
- package/.grok/skills/animate-expo/RECIPES.md +0 -385
- package/.grok/skills/animate-expo/SKILL.md +0 -263
- package/.grok/skills/animation-vocabulary/SKILL.md +0 -181
- package/.grok/skills/apple-design/SKILL.md +0 -290
- package/.grok/skills/ask-sonner/API.md +0 -64
- package/.grok/skills/ask-sonner/SKILL.md +0 -88
- package/.grok/skills/backend-development/SKILL.md +0 -272
- package/.grok/skills/backend-development/references/api-design-guidelines.md +0 -95
- package/.grok/skills/backend-development/references/query-and-database-best-practices.md +0 -53
- package/.grok/skills/backend-development/references/security-checklist.md +0 -60
- package/.grok/skills/emil-design-eng/SKILL.md +0 -674
- package/.grok/skills/find-animation-opportunities/SKILL.md +0 -140
- package/.grok/skills/improve-animations/AUDIT.md +0 -115
- package/.grok/skills/improve-animations/PLAN-TEMPLATE.md +0 -73
- package/.grok/skills/improve-animations/SKILL.md +0 -109
- package/.grok/skills/mobile-native/SKILL.md +0 -311
- package/.grok/skills/pick-ui-library/SKILL.md +0 -85
- package/.grok/skills/prototype/PICKER.md +0 -197
- package/.grok/skills/prototype/SKILL.md +0 -98
- package/.grok/skills/review-animations/SKILL.md +0 -120
- package/.grok/skills/review-animations/STANDARDS.md +0 -187
- package/.grok/skills/write-swift/SKILL.md +0 -396
- /package/{.gemini → .agents}/skills/ai-engineering-loop/references/loop-commands.md +0 -0
- /package/{.gemini → .agents}/skills/ai-engineering-loop/references/loop-deliver.md +0 -0
- /package/{.gemini → .agents}/skills/ai-engineering-loop/references/loop-goal.md +0 -0
- /package/{.gemini → .agents}/skills/ai-engineering-loop/references/loop-maker.md +0 -0
- /package/{.gemini → .agents}/skills/ai-engineering-loop/references/loop-review.md +0 -0
- /package/{.gemini → .agents}/skills/ai-engineering-loop/references/loop-risky.md +0 -0
- /package/{.gemini → .agents}/skills/ai-engineering-loop/references/loop-verify.md +0 -0
package/lib/sync-hosts.js
CHANGED
|
@@ -2,6 +2,9 @@
|
|
|
2
2
|
|
|
3
3
|
const fs = require('fs');
|
|
4
4
|
const path = require('path');
|
|
5
|
+
const { AGENTS, FORMATS, renderAgent, agentFileName } = require('./hosts/agent-formats.js');
|
|
6
|
+
const { HOSTS, HOST_IDS, SHARED_SKILLS_DIR, usesSharedSkills } = require('./hosts/registry.js');
|
|
7
|
+
const { detectHosts } = require('./hosts/detect.js');
|
|
5
8
|
const {
|
|
6
9
|
homeDir,
|
|
7
10
|
sha256,
|
|
@@ -22,16 +25,6 @@ const HOST_PACKS = Object.freeze(['core', 'backend', 'design', 'quality']);
|
|
|
22
25
|
const DEFAULT_HOST_PACKS = Object.freeze(['core']);
|
|
23
26
|
const MANIFEST_FILE = 'host-manifest.json';
|
|
24
27
|
|
|
25
|
-
function applyGrokSkillOverlay(content) {
|
|
26
|
-
const normalized = String(content).replace(/\r\n?/g, '\n');
|
|
27
|
-
const match = normalized.match(/^---\n([\s\S]*?)\n---\n/);
|
|
28
|
-
if (!match) return normalized;
|
|
29
|
-
const yaml = match[1];
|
|
30
|
-
if (/^user-invocable:\s*true\s*$/m.test(yaml)) return normalized;
|
|
31
|
-
const nextYaml = `${yaml.replace(/\s*$/, '')}\nuser-invocable: true`;
|
|
32
|
-
return `---\n${nextYaml}\n---\n${normalized.slice(match[0].length)}`;
|
|
33
|
-
}
|
|
34
|
-
|
|
35
28
|
const BACKEND_SKILL_FILES = [
|
|
36
29
|
'SKILL.md',
|
|
37
30
|
'references/api-design-guidelines.md',
|
|
@@ -71,24 +64,22 @@ const EMIL_KOWALSKI_SKILL_FILES = Object.freeze({
|
|
|
71
64
|
'write-swift': ['SKILL.md']
|
|
72
65
|
});
|
|
73
66
|
|
|
74
|
-
function backendSkillFiles(srcRoot, destRoot
|
|
67
|
+
function backendSkillFiles(srcRoot, destRoot) {
|
|
75
68
|
return BACKEND_SKILL_FILES.map((file) => ({
|
|
76
69
|
src: path.posix.join(srcRoot, file),
|
|
77
70
|
dest: path.join(destRoot, file),
|
|
78
71
|
mode: 'upsert',
|
|
79
|
-
pack: 'backend'
|
|
80
|
-
...(grokSkillOverlay && file === 'SKILL.md' ? { grokSkillOverlay: true } : {})
|
|
72
|
+
pack: 'backend'
|
|
81
73
|
}));
|
|
82
74
|
}
|
|
83
75
|
|
|
84
|
-
function emilKowalskiSkillFiles(srcRoot, destRoot
|
|
76
|
+
function emilKowalskiSkillFiles(srcRoot, destRoot) {
|
|
85
77
|
return EMIL_KOWALSKI_SKILLS.flatMap((skill) => (
|
|
86
78
|
EMIL_KOWALSKI_SKILL_FILES[skill].map((file) => ({
|
|
87
79
|
src: path.posix.join(srcRoot, skill, file),
|
|
88
80
|
dest: path.join(destRoot, skill, file),
|
|
89
81
|
mode: 'upsert',
|
|
90
|
-
pack: 'design'
|
|
91
|
-
...(grokSkillOverlay && file === 'SKILL.md' ? { grokSkillOverlay: true } : {})
|
|
82
|
+
pack: 'design'
|
|
92
83
|
}))
|
|
93
84
|
));
|
|
94
85
|
}
|
|
@@ -97,17 +88,15 @@ function emilKowalskiSkillFiles(srcRoot, destRoot, { grokSkillOverlay = false }
|
|
|
97
88
|
// pack (ael-code-simplifier, ael-receiving-code-review) is opt-in.
|
|
98
89
|
const QUALITY_SKILLS = Object.freeze(['ael-code-simplifier', 'ael-receiving-code-review']);
|
|
99
90
|
|
|
100
|
-
function adoptedSkillFiles(destRoot
|
|
101
|
-
const overlay = grokSkillOverlay ? { grokSkillOverlay: true } : {};
|
|
91
|
+
function adoptedSkillFiles(destRoot) {
|
|
102
92
|
return [
|
|
103
|
-
{ src: 'adapters/project-onboarding/SKILL.md', dest: path.join(destRoot, 'project-onboarding/SKILL.md'), mode: 'upsert'
|
|
93
|
+
{ src: 'adapters/project-onboarding/SKILL.md', dest: path.join(destRoot, 'project-onboarding/SKILL.md'), mode: 'upsert' },
|
|
104
94
|
{ src: 'adapters/project-onboarding/references/output.md', dest: path.join(destRoot, 'project-onboarding/references/output.md'), mode: 'upsert' },
|
|
105
95
|
...QUALITY_SKILLS.map((skill) => ({
|
|
106
96
|
src: `adapters/quality/skills/${skill}/SKILL.md`,
|
|
107
97
|
dest: path.join(destRoot, skill, 'SKILL.md'),
|
|
108
98
|
mode: 'upsert',
|
|
109
|
-
pack: 'quality'
|
|
110
|
-
...overlay
|
|
99
|
+
pack: 'quality'
|
|
111
100
|
}))
|
|
112
101
|
];
|
|
113
102
|
}
|
|
@@ -117,6 +106,7 @@ const LOOP_REFERENCE_FILES = Object.freeze([
|
|
|
117
106
|
'loop-commands.md',
|
|
118
107
|
'loop-deliver.md',
|
|
119
108
|
'loop-goal.md',
|
|
109
|
+
'loop-hosts.md',
|
|
120
110
|
'loop-maker.md',
|
|
121
111
|
'loop-review.md',
|
|
122
112
|
'loop-risky.md',
|
|
@@ -131,87 +121,123 @@ function loopReferenceFiles(srcDir, destDir) {
|
|
|
131
121
|
}));
|
|
132
122
|
}
|
|
133
123
|
|
|
134
|
-
|
|
135
|
-
|
|
136
|
-
|
|
137
|
-
|
|
138
|
-
|
|
124
|
+
// The host-neutral core skill (#48): one source, byte-identical everywhere.
|
|
125
|
+
const CORE_SKILL_SRC = '.agents/skills/ai-engineering-loop';
|
|
126
|
+
|
|
127
|
+
// Every skill a host's skill folder gets: core loop skill, helpers, packs.
|
|
128
|
+
function skillFolderFiles(skillsDir) {
|
|
139
129
|
return [
|
|
140
|
-
{
|
|
141
|
-
|
|
142
|
-
|
|
143
|
-
|
|
144
|
-
|
|
145
|
-
|
|
146
|
-
|
|
147
|
-
|
|
148
|
-
{ src: 'adapters/dot/skills/task-impact-inquiry/SKILL.md', dest: path.join(claude, 'skills/task-impact-inquiry/SKILL.md'), mode: 'upsert' },
|
|
149
|
-
{ src: 'adapters/generate-adapter/SKILL.md', dest: path.join(claude, 'skills/generate-adapter/SKILL.md'), mode: 'upsert' },
|
|
150
|
-
{ src: 'adapters/generate-workflow/SKILL.md', dest: path.join(claude, 'skills/generate-workflow/SKILL.md'), mode: 'upsert' },
|
|
151
|
-
...adoptedSkillFiles(path.join(claude, 'skills')),
|
|
152
|
-
{ src: '.claude/agents/devil-advocate.md', dest: path.join(claude, 'agents/devil-advocate.md'), mode: 'upsert' },
|
|
153
|
-
{ src: '.claude/agents/judge.md', dest: path.join(claude, 'agents/judge.md'), mode: 'upsert' },
|
|
154
|
-
{ src: '.claude/commands/ai-engineering-loop.md', dest: path.join(claude, 'commands/ai-engineering-loop.md'), mode: 'upsert' }
|
|
155
|
-
]
|
|
156
|
-
},
|
|
157
|
-
{
|
|
158
|
-
id: 'grok',
|
|
159
|
-
root: grok,
|
|
160
|
-
files: [
|
|
161
|
-
{ src: '.grok/skills/ai-engineering-loop/SKILL.md', dest: path.join(grok, 'skills/ai-engineering-loop/SKILL.md'), mode: 'upsert', grokSkillOverlay: true },
|
|
162
|
-
...loopReferenceFiles('.grok/skills/ai-engineering-loop', path.join(grok, 'skills/ai-engineering-loop')),
|
|
163
|
-
...backendSkillFiles('.grok/skills/backend-development', path.join(grok, 'skills/backend-development'), { grokSkillOverlay: true }),
|
|
164
|
-
...emilKowalskiSkillFiles('.grok/skills', path.join(grok, 'skills'), { grokSkillOverlay: true }),
|
|
165
|
-
{ src: 'adapters/dot/skills/task-impact-inquiry/SKILL.md', dest: path.join(grok, 'skills/task-impact-inquiry/SKILL.md'), mode: 'upsert', grokSkillOverlay: true },
|
|
166
|
-
{ src: 'adapters/generate-adapter/SKILL.md', dest: path.join(grok, 'skills/generate-adapter/SKILL.md'), mode: 'upsert', grokSkillOverlay: true },
|
|
167
|
-
{ src: 'adapters/generate-workflow/SKILL.md', dest: path.join(grok, 'skills/generate-workflow/SKILL.md'), mode: 'upsert', grokSkillOverlay: true },
|
|
168
|
-
...adoptedSkillFiles(path.join(grok, 'skills'), { grokSkillOverlay: true }),
|
|
169
|
-
{ src: '.grok/agents/devil-advocate.md', dest: path.join(grok, 'agents/devil-advocate.md'), mode: 'upsert' },
|
|
170
|
-
{ src: '.grok/agents/judge.md', dest: path.join(grok, 'agents/judge.md'), mode: 'upsert' },
|
|
171
|
-
{ src: '.grok/commands/ai-engineering-loop.md', dest: path.join(grok, 'commands/ai-engineering-loop.md'), mode: 'upsert' }
|
|
172
|
-
]
|
|
173
|
-
},
|
|
174
|
-
{
|
|
175
|
-
id: 'gemini',
|
|
176
|
-
root: gemini,
|
|
177
|
-
files: [
|
|
178
|
-
{ src: '.gemini/skills/ai-engineering-loop/SKILL.md', dest: path.join(gemini, 'config/skills/ai-engineering-loop/SKILL.md'), mode: 'upsert' },
|
|
179
|
-
...loopReferenceFiles('.gemini/skills/ai-engineering-loop', path.join(gemini, 'config/skills/ai-engineering-loop')),
|
|
180
|
-
...backendSkillFiles('.gemini/skills/backend-development', path.join(gemini, 'config/skills/backend-development')),
|
|
181
|
-
...emilKowalskiSkillFiles('.gemini/skills', path.join(gemini, 'config/skills')),
|
|
182
|
-
{ src: 'adapters/dot/skills/task-impact-inquiry/SKILL.md', dest: path.join(gemini, 'config/skills/task-impact-inquiry/SKILL.md'), mode: 'upsert' },
|
|
183
|
-
{ src: 'adapters/generate-adapter/SKILL.md', dest: path.join(gemini, 'config/skills/generate-adapter/SKILL.md'), mode: 'upsert' },
|
|
184
|
-
{ src: 'adapters/generate-workflow/SKILL.md', dest: path.join(gemini, 'config/skills/generate-workflow/SKILL.md'), mode: 'upsert' },
|
|
185
|
-
...adoptedSkillFiles(path.join(gemini, 'config/skills'))
|
|
186
|
-
]
|
|
187
|
-
},
|
|
188
|
-
{
|
|
189
|
-
id: 'antigravity',
|
|
190
|
-
root: agents,
|
|
191
|
-
files: [
|
|
192
|
-
...backendSkillFiles('.agents/skills/backend-development', path.join(agents, 'skills/backend-development')),
|
|
193
|
-
...emilKowalskiSkillFiles('.agents/skills', path.join(agents, 'skills')),
|
|
194
|
-
...adoptedSkillFiles(path.join(agents, 'skills')),
|
|
195
|
-
{ src: '.agents/devil-advocate.md', dest: path.join(agents, 'devil-advocate.md'), mode: 'upsert' },
|
|
196
|
-
{ src: '.agents/judge.md', dest: path.join(agents, 'judge.md'), mode: 'upsert' },
|
|
197
|
-
{ src: '.agents/workflows/ai-engineering-loop.md', dest: path.join(agents, 'workflows/ai-engineering-loop.md'), mode: 'upsert' }
|
|
198
|
-
]
|
|
199
|
-
},
|
|
200
|
-
{
|
|
201
|
-
id: 'dot',
|
|
202
|
-
root: null,
|
|
203
|
-
files: [
|
|
204
|
-
{ src: 'adapters/dot/skills/dot-dev-skill-router/SKILL.md', dest: path.join(claude, 'skills/dot-dev-skill-router/SKILL.md'), mode: 'update-if-exists', hostRoot: claude },
|
|
205
|
-
{ src: 'adapters/dot/skills/dot-dev-workflow/SKILL.md', dest: path.join(claude, 'skills/dot-dev-workflow/SKILL.md'), mode: 'update-if-exists', hostRoot: claude },
|
|
206
|
-
{ src: 'adapters/dot/skills/dot-dev-skill-router/SKILL.md', dest: path.join(grok, 'skills/dot-dev-skill-router/SKILL.md'), mode: 'update-if-exists', hostRoot: grok, grokSkillOverlay: true },
|
|
207
|
-
{ src: 'adapters/dot/skills/dot-dev-workflow/SKILL.md', dest: path.join(grok, 'skills/dot-dev-workflow/SKILL.md'), mode: 'update-if-exists', hostRoot: grok, grokSkillOverlay: true },
|
|
208
|
-
{ src: 'adapters/dot/skills/dot-dev-skill-router/SKILL.md', dest: path.join(gemini, 'config/skills/dot-dev-skill-router/SKILL.md'), mode: 'update-if-exists', hostRoot: gemini },
|
|
209
|
-
{ src: 'adapters/dot/skills/dot-dev-workflow/SKILL.md', dest: path.join(gemini, 'config/skills/dot-dev-workflow/SKILL.md'), mode: 'update-if-exists', hostRoot: gemini }
|
|
210
|
-
]
|
|
211
|
-
}
|
|
130
|
+
{ src: `${CORE_SKILL_SRC}/SKILL.md`, dest: path.join(skillsDir, 'ai-engineering-loop/SKILL.md'), mode: 'upsert' },
|
|
131
|
+
...loopReferenceFiles(CORE_SKILL_SRC, path.join(skillsDir, 'ai-engineering-loop')),
|
|
132
|
+
...backendSkillFiles('.agents/skills/backend-development', path.join(skillsDir, 'backend-development')),
|
|
133
|
+
...emilKowalskiSkillFiles('.agents/skills', skillsDir),
|
|
134
|
+
{ src: 'adapters/dot/skills/task-impact-inquiry/SKILL.md', dest: path.join(skillsDir, 'task-impact-inquiry/SKILL.md'), mode: 'upsert' },
|
|
135
|
+
{ src: 'adapters/generate-adapter/SKILL.md', dest: path.join(skillsDir, 'generate-adapter/SKILL.md'), mode: 'upsert' },
|
|
136
|
+
{ src: 'adapters/generate-workflow/SKILL.md', dest: path.join(skillsDir, 'generate-workflow/SKILL.md'), mode: 'upsert' },
|
|
137
|
+
...adoptedSkillFiles(skillsDir)
|
|
212
138
|
];
|
|
213
139
|
}
|
|
214
140
|
|
|
141
|
+
function agentFiles(host, home) {
|
|
142
|
+
if (!host.agents) return [];
|
|
143
|
+
const dir = path.join(home, host.agents.dir);
|
|
144
|
+
const format = FORMATS[host.agents.format];
|
|
145
|
+
if (!format) throw new Error(`${host.id}: unknown agent format ${host.agents.format}`);
|
|
146
|
+
return AGENTS.map((name) => {
|
|
147
|
+
const dest = path.join(dir, agentFileName(host.agents.format, name));
|
|
148
|
+
// Canonical repo copies (Claude, Grok) ship as files; others are rendered.
|
|
149
|
+
if (format.src) return { src: format.src(name), dest, mode: 'upsert' };
|
|
150
|
+
return { src: `agents/shared/${name}.body.md`, dest, mode: 'upsert', agentFormat: host.agents.format, agentName: name };
|
|
151
|
+
});
|
|
152
|
+
}
|
|
153
|
+
|
|
154
|
+
// Which hosts get files. After `setup` / `hosts enable|disable` the saved
|
|
155
|
+
// config decides. Before that (legacy installs) a host counts when one of its
|
|
156
|
+
// config directories exists, exactly like earlier releases; PATH binaries only
|
|
157
|
+
// feed `setup` and `hosts list`, so an automatic sync never creates folders for
|
|
158
|
+
// an agent the user has not opted into.
|
|
159
|
+
function resolveHostSelection(home) {
|
|
160
|
+
const config = readUserConfig(home);
|
|
161
|
+
const saved = config.hosts && typeof config.hosts === 'object' ? config.hosts : null;
|
|
162
|
+
if (saved && Array.isArray(saved.enabled)) {
|
|
163
|
+
const enabled = new Set(saved.enabled.filter((id) => HOST_IDS.includes(id)));
|
|
164
|
+
const disabled = new Set((Array.isArray(saved.disabled) ? saved.disabled : []).filter((id) => HOST_IDS.includes(id) && !enabled.has(id)));
|
|
165
|
+
return { enabled, disabled, source: 'config', mode: saved.mode === 'auto' ? 'auto' : 'manual' };
|
|
166
|
+
}
|
|
167
|
+
const enabled = new Set(detectHosts({ home, env: { PATH: '' } }).filter((d) => d.detected).map((d) => d.id));
|
|
168
|
+
// An earlier sync already installed files for this host: keep it.
|
|
169
|
+
const tracked = Object.keys(readHostManifest(home).files).map((file) => path.resolve(file));
|
|
170
|
+
for (const host of HOSTS) {
|
|
171
|
+
const dirs = [usesSharedSkills(host) ? null : host.skills.dir, host.agents && host.agents.dir].filter(Boolean)
|
|
172
|
+
.map((dir) => path.resolve(home, dir) + path.sep);
|
|
173
|
+
if (tracked.some((file) => dirs.some((dir) => file.startsWith(dir)))) enabled.add(host.id);
|
|
174
|
+
}
|
|
175
|
+
return { enabled, disabled: new Set(), source: 'legacy-dirs', mode: null };
|
|
176
|
+
}
|
|
177
|
+
|
|
178
|
+
// Groups of files per host, plus the shared ~/.agents/skills folder and
|
|
179
|
+
// update-only DOT skills. A file wanted by any enabled group is never pruned
|
|
180
|
+
// on behalf of a disabled one (Antigravity IDE and CLI share an agents dir).
|
|
181
|
+
function hostFileMap(home, selection = resolveHostSelection(home)) {
|
|
182
|
+
const groups = [];
|
|
183
|
+
const sharedUsers = HOSTS.filter((host) => usesSharedSkills(host));
|
|
184
|
+
const sharedEnabled = sharedUsers.some((host) => selection.enabled.has(host.id));
|
|
185
|
+
const sharedDisabled = !sharedEnabled && selection.source === 'config' && sharedUsers.some((host) => selection.disabled.has(host.id));
|
|
186
|
+
const skillDirs = [];
|
|
187
|
+
for (const host of HOSTS) {
|
|
188
|
+
const files = [];
|
|
189
|
+
if (!usesSharedSkills(host)) files.push(...skillFolderFiles(path.join(home, host.skills.dir)));
|
|
190
|
+
files.push(...agentFiles(host, home));
|
|
191
|
+
const enabled = selection.enabled.has(host.id);
|
|
192
|
+
if (enabled && !usesSharedSkills(host)) skillDirs.push(path.join(home, host.skills.dir));
|
|
193
|
+
groups.push({ id: host.id, enabled, disabled: selection.disabled.has(host.id), files });
|
|
194
|
+
}
|
|
195
|
+
groups.push({
|
|
196
|
+
id: 'shared',
|
|
197
|
+
enabled: sharedEnabled,
|
|
198
|
+
disabled: sharedDisabled,
|
|
199
|
+
files: skillFolderFiles(path.join(home, SHARED_SKILLS_DIR))
|
|
200
|
+
});
|
|
201
|
+
if (sharedEnabled) skillDirs.push(path.join(home, SHARED_SKILLS_DIR));
|
|
202
|
+
groups.push({
|
|
203
|
+
id: 'dot',
|
|
204
|
+
enabled: true,
|
|
205
|
+
disabled: false,
|
|
206
|
+
files: [...new Set(skillDirs)].flatMap((dir) => DOT_SKILLS.map((skill) => ({
|
|
207
|
+
src: `adapters/dot/skills/${skill}/SKILL.md`,
|
|
208
|
+
dest: path.join(dir, skill, 'SKILL.md'),
|
|
209
|
+
mode: 'update-if-exists'
|
|
210
|
+
})))
|
|
211
|
+
});
|
|
212
|
+
const wanted = new Set();
|
|
213
|
+
for (const group of groups) {
|
|
214
|
+
if (!group.enabled) continue;
|
|
215
|
+
group.files = group.files.filter((file) => {
|
|
216
|
+
const key = path.resolve(file.dest);
|
|
217
|
+
if (wanted.has(key)) return false;
|
|
218
|
+
wanted.add(key);
|
|
219
|
+
return true;
|
|
220
|
+
});
|
|
221
|
+
}
|
|
222
|
+
for (const group of groups) {
|
|
223
|
+
if (group.enabled) continue;
|
|
224
|
+
group.files = group.files.filter((file) => !wanted.has(path.resolve(file.dest)));
|
|
225
|
+
}
|
|
226
|
+
return groups;
|
|
227
|
+
}
|
|
228
|
+
|
|
229
|
+
const DOT_SKILLS = Object.freeze(['dot-dev-skill-router', 'dot-dev-workflow']);
|
|
230
|
+
|
|
231
|
+
// Directories AEL may own files under (obsolete-file cleanup is limited to them).
|
|
232
|
+
function managedRoots(home) {
|
|
233
|
+
const roots = new Set([path.join(home, '.agents')]);
|
|
234
|
+
for (const host of HOSTS) {
|
|
235
|
+
if (!usesSharedSkills(host)) roots.add(path.dirname(path.join(home, host.skills.dir)));
|
|
236
|
+
if (host.agents) roots.add(path.dirname(path.join(home, host.agents.dir)));
|
|
237
|
+
}
|
|
238
|
+
return [...roots].map((root) => path.resolve(root));
|
|
239
|
+
}
|
|
240
|
+
|
|
215
241
|
function destExists(dest) {
|
|
216
242
|
try {
|
|
217
243
|
fs.lstatSync(dest);
|
|
@@ -290,12 +316,13 @@ function readFileText(dest) {
|
|
|
290
316
|
}
|
|
291
317
|
|
|
292
318
|
function packageContent(root, file) {
|
|
319
|
+
if (file.agentFormat) return renderAgent(root, file.agentFormat, file.agentName);
|
|
293
320
|
const srcAbs = path.join(root, file.src);
|
|
294
|
-
|
|
295
|
-
if (file.grokSkillOverlay) content = applyGrokSkillOverlay(content);
|
|
296
|
-
return content;
|
|
321
|
+
return fs.readFileSync(srcAbs, 'utf8').replace(/\r\n?/g, '\n');
|
|
297
322
|
}
|
|
298
323
|
|
|
324
|
+
|
|
325
|
+
|
|
299
326
|
// Pack selection precedence: explicit argument > saved user config > legacy
|
|
300
327
|
// auto-detect (a non-core pack stays selected while any of its files is already
|
|
301
328
|
// installed, so upgrading never silently freezes an existing install).
|
|
@@ -304,7 +331,7 @@ function resolvePacks({ packs, home }) {
|
|
|
304
331
|
const config = readUserConfig(home);
|
|
305
332
|
if (Array.isArray(config.hostPacks)) return { packs: normalizePacks(config.hostPacks), source: 'config' };
|
|
306
333
|
const detected = new Set(DEFAULT_HOST_PACKS);
|
|
307
|
-
for (const group of hostFileMap(home)) {
|
|
334
|
+
for (const group of hostFileMap(home, { enabled: new Set(HOST_IDS), disabled: new Set(), source: 'all' })) {
|
|
308
335
|
for (const file of group.files) {
|
|
309
336
|
if (file.pack && file.pack !== 'core' && destExists(file.dest)) detected.add(file.pack);
|
|
310
337
|
}
|
|
@@ -312,14 +339,15 @@ function resolvePacks({ packs, home }) {
|
|
|
312
339
|
return { packs: normalizePacks([...detected]), source: detected.size > 1 ? 'detected' : 'default' };
|
|
313
340
|
}
|
|
314
341
|
|
|
315
|
-
function planHostSync({ packageRoot: root = packageRoot(), home = homeDir(), packs = null, prune = false } = {}) {
|
|
342
|
+
function planHostSync({ packageRoot: root = packageRoot(), home = homeDir(), packs = null, prune = false, hosts = null } = {}) {
|
|
316
343
|
const results = [];
|
|
317
344
|
const selection = resolvePacks({ packs, home });
|
|
345
|
+
const hostSelection = hosts || resolveHostSelection(home);
|
|
318
346
|
const manifest = readHostManifest(home);
|
|
319
|
-
|
|
347
|
+
const groups = hostFileMap(home, hostSelection);
|
|
348
|
+
for (const group of groups) {
|
|
320
349
|
for (const file of group.files) {
|
|
321
350
|
const srcAbs = path.join(root, file.src);
|
|
322
|
-
const hostRoot = file.hostRoot || group.root;
|
|
323
351
|
const pack = file.pack || 'core';
|
|
324
352
|
const item = {
|
|
325
353
|
id: group.id,
|
|
@@ -328,8 +356,17 @@ function planHostSync({ packageRoot: root = packageRoot(), home = homeDir(), pac
|
|
|
328
356
|
mode: file.mode,
|
|
329
357
|
pack
|
|
330
358
|
};
|
|
331
|
-
if (
|
|
332
|
-
|
|
359
|
+
if (!group.enabled) {
|
|
360
|
+
const existing = group.disabled && destExists(file.dest) ? readFileText(file.dest) : null;
|
|
361
|
+
if (existing === null) {
|
|
362
|
+
results.push({ ...item, action: 'skip', reason: group.disabled ? 'host-disabled' : 'host-missing' });
|
|
363
|
+
continue;
|
|
364
|
+
}
|
|
365
|
+
// `hosts disable`: remove what AEL wrote, keep what the user edited.
|
|
366
|
+
const tracked = manifest.files[file.dest];
|
|
367
|
+
results.push(tracked && tracked.sha256 === sha256(existing)
|
|
368
|
+
? { ...item, action: 'prune', reason: 'host-disabled' }
|
|
369
|
+
: { ...item, action: 'skip', reason: 'modified' });
|
|
333
370
|
continue;
|
|
334
371
|
}
|
|
335
372
|
if (!fs.existsSync(srcAbs)) {
|
|
@@ -381,7 +418,7 @@ function planHostSync({ packageRoot: root = packageRoot(), home = homeDir(), pac
|
|
|
381
418
|
// earlier sync but no longer shipped (for example a renamed skill). Removed
|
|
382
419
|
// when still byte-identical to what AEL wrote; edited ones are kept.
|
|
383
420
|
const known = new Set(results.map((item) => path.resolve(item.dest)));
|
|
384
|
-
const hostRoots =
|
|
421
|
+
const hostRoots = managedRoots(home);
|
|
385
422
|
for (const [dest, tracked] of Object.entries(manifest.files || {})) {
|
|
386
423
|
const abs = path.resolve(dest);
|
|
387
424
|
if (known.has(abs)) continue;
|
|
@@ -398,6 +435,8 @@ function planHostSync({ packageRoot: root = packageRoot(), home = homeDir(), pac
|
|
|
398
435
|
}
|
|
399
436
|
results.packs = selection.packs;
|
|
400
437
|
results.packSource = selection.source;
|
|
438
|
+
results.hosts = [...hostSelection.enabled];
|
|
439
|
+
results.hostSource = hostSelection.source;
|
|
401
440
|
return results;
|
|
402
441
|
}
|
|
403
442
|
|
|
@@ -406,7 +445,7 @@ function removeEmptyParents(dir, home) {
|
|
|
406
445
|
let current = path.resolve(dir);
|
|
407
446
|
const stop = path.resolve(home);
|
|
408
447
|
for (let depth = 0; depth < 3; depth += 1) {
|
|
409
|
-
if (path.basename(current)
|
|
448
|
+
if (['skills', 'agents'].includes(path.basename(current)) || path.dirname(current) === stop || current === stop) return;
|
|
410
449
|
try {
|
|
411
450
|
if (fs.readdirSync(current).length > 0) return;
|
|
412
451
|
fs.rmdirSync(current);
|
|
@@ -443,9 +482,10 @@ function applyHostSync({
|
|
|
443
482
|
dryRun = false,
|
|
444
483
|
packs = null,
|
|
445
484
|
prune = false,
|
|
446
|
-
version = null
|
|
485
|
+
version = null,
|
|
486
|
+
hosts = null
|
|
447
487
|
} = {}) {
|
|
448
|
-
const plan = planHostSync({ packageRoot: root, home, packs, prune });
|
|
488
|
+
const plan = planHostSync({ packageRoot: root, home, packs, prune, hosts });
|
|
449
489
|
const applied = [];
|
|
450
490
|
const manifest = readHostManifest(home);
|
|
451
491
|
let manifestChanged = false;
|
|
@@ -515,6 +555,8 @@ function applyHostSync({
|
|
|
515
555
|
if (!dryRun && packs != null) writeUserConfig({ hostPacks: plan.packs }, home);
|
|
516
556
|
applied.packs = plan.packs;
|
|
517
557
|
applied.packSource = plan.packSource;
|
|
558
|
+
applied.hosts = plan.hosts;
|
|
559
|
+
applied.hostSource = plan.hostSource;
|
|
518
560
|
return applied;
|
|
519
561
|
}
|
|
520
562
|
|
|
@@ -591,10 +633,11 @@ module.exports = {
|
|
|
591
633
|
hostSkillStatus,
|
|
592
634
|
packageRoot,
|
|
593
635
|
homeDir,
|
|
594
|
-
applyGrokSkillOverlay,
|
|
595
636
|
EMIL_KOWALSKI_SKILLS,
|
|
596
637
|
EMIL_KOWALSKI_SKILL_FILES,
|
|
597
638
|
hostFileMap,
|
|
639
|
+
resolveHostSelection,
|
|
640
|
+
managedRoots,
|
|
598
641
|
planHostSync,
|
|
599
642
|
applyHostSync,
|
|
600
643
|
summarizeHostSync,
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "ai-engineering-loop",
|
|
3
|
-
"version": "1.
|
|
3
|
+
"version": "1.15.0",
|
|
4
4
|
"description": "A visual workspace that helps AI coding agents plan, build, review, and ship reliable software.",
|
|
5
5
|
"main": "bin/ai-engineering-loop.js",
|
|
6
6
|
"bin": {
|
|
@@ -21,9 +21,7 @@
|
|
|
21
21
|
"evals/",
|
|
22
22
|
".agents/",
|
|
23
23
|
".grok/",
|
|
24
|
-
".gemini/skills/",
|
|
25
24
|
".claude/agents/",
|
|
26
|
-
".claude/commands/",
|
|
27
25
|
".claude/skills/",
|
|
28
26
|
"LICENSE",
|
|
29
27
|
"THIRD_PARTY_NOTICES.md",
|
|
@@ -43,6 +41,7 @@
|
|
|
43
41
|
"prepublishOnly": "npm run check:skills && npm test && npm run doctor && npm run eval && npm run audit:package",
|
|
44
42
|
"build:skills": "node scripts/build-host-skills.js",
|
|
45
43
|
"check:skills": "node scripts/build-host-skills.js --check",
|
|
44
|
+
"build:hosts-table": "node scripts/build-host-table.js",
|
|
46
45
|
"measure": "node scripts/measure.js"
|
|
47
46
|
},
|
|
48
47
|
"engines": {
|
|
@@ -1,79 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: devil-advocate
|
|
3
|
-
description: Use this agent after deterministic tests pass, to adversarially review a git diff against a Goal Contract. Returns a Finding Ledger. Typical triggers include a completed Maker pass and an explicit devil's advocate request.
|
|
4
|
-
tools: view_file, grep_search, list_dir, run_command
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
You are the Devil's Advocate for the AI Engineering Loop. You are read-only. You never modify application source and never commit.
|
|
8
|
-
|
|
9
|
-
## Budget (hard stop)
|
|
10
|
-
|
|
11
|
-
Finish in at most 8 tool calls, then emit the Finding Ledger. Do not explore the rest of the repo. Do not spawn children. Do not run git log.
|
|
12
|
-
|
|
13
|
-
Default to a lean review: spend detail where it protects correctness, not on prose. Treat the context pack as scarce. Prefer one precise quote over a long explanation.
|
|
14
|
-
|
|
15
|
-
## Input barrier
|
|
16
|
-
|
|
17
|
-
Use only:
|
|
18
|
-
|
|
19
|
-
1. The diff or smart diff-hunk pack path in the spawn prompt. Read that file first. Do not run git diff if a diff path was given.
|
|
20
|
-
2. Goal Contract path (if given).
|
|
21
|
-
3. Verification log path (if given).
|
|
22
|
-
4. conventions.md path (if given). At most one extra read.
|
|
23
|
-
5. At most 8 source files that appear as paths in the diff.
|
|
24
|
-
|
|
25
|
-
Skip: `*.css`, files named like `*-css.ts` or `report-css.ts`, generated/vendor dirs, and any file where the diff hunk already contains enough evidence. Prefer quoting the hunk over opening the whole file.
|
|
26
|
-
|
|
27
|
-
Do not ask for Maker rationale.
|
|
28
|
-
|
|
29
|
-
On iteration 2 or later, review only the changed hunks since the previous Finding Ledger plus previously unresolved findings. A smart diff-hunk pack already contains that shape; use it instead of opening full files when possible. Do not re-litigate accepted or dismissed findings unless the new diff changes their evidence.
|
|
30
|
-
|
|
31
|
-
## Two axes (do not merge)
|
|
32
|
-
|
|
33
|
-
Report Spec and Standards as separate findings. Do not rerank one axis with the other. A change can pass Spec and fail Standards, or the reverse. Do not spawn children to split axes.
|
|
34
|
-
|
|
35
|
-
**Spec** (`axis: "spec"`): Goal Contract acceptance criteria, correctness, error handling, security, concurrency, tests that fail to prove an AC, happy-path-only suite vs written failure table. BLOCKER or HIGH only for a real AC breach or runtime defect.
|
|
36
|
-
|
|
37
|
-
**Standards** (`axis: "standards"`): `.ai-engineering-loop/conventions.md` plus the smell baseline below. Judgement calls: severity MEDIUM or LOW. Set `hardConvention: true` only when conventions.md states a hard rule that this hunk violates. A smell that hides an AC defect is Spec, not Standards.
|
|
38
|
-
|
|
39
|
-
Skip style nits unless they hide a defect.
|
|
40
|
-
|
|
41
|
-
Smell baseline (judgement only; skip if tooling already enforces; repo conventions override): Mysterious Name; Duplicated Code; Feature Envy; Data Clumps; Primitive Obsession; Repeated Switches; Shotgun Surgery; Divergent Change; Speculative Generality; Message Chains; Middle Man; Refused Bequest.
|
|
42
|
-
|
|
43
|
-
## Output
|
|
44
|
-
|
|
45
|
-
Return a Finding Ledger as a fenced JSON block and stop:
|
|
46
|
-
|
|
47
|
-
```json
|
|
48
|
-
{
|
|
49
|
-
"iteration": 1,
|
|
50
|
-
"executionMode": "TRUE_INDEPENDENT_AGENT",
|
|
51
|
-
"findings": [
|
|
52
|
-
{
|
|
53
|
-
"id": "DA-01",
|
|
54
|
-
"axis": "spec",
|
|
55
|
-
"hardConvention": false,
|
|
56
|
-
"topic": "correctness",
|
|
57
|
-
"validity": "VALID",
|
|
58
|
-
"severity": "BLOCKER",
|
|
59
|
-
"disposition": "STRONG",
|
|
60
|
-
"location": "path/to/file.ext#L12-L20",
|
|
61
|
-
"acceptanceCriteria": "AC-1",
|
|
62
|
-
"failureScenario": "Concrete failing case",
|
|
63
|
-
"reproduction": "Steps to reproduce",
|
|
64
|
-
"evidence": "Hunk or line you read",
|
|
65
|
-
"concreteAlternativeDiff": "diff snippet"
|
|
66
|
-
}
|
|
67
|
-
]
|
|
68
|
-
}
|
|
69
|
-
```
|
|
70
|
-
|
|
71
|
-
Rules: axis is spec or standards (default spec). hardConvention is boolean, default false. validity VALID or INVALID; severity BLOCKER, HIGH, MEDIUM, or LOW; disposition STRONG, ACCEPTABLE, or WEAK. VALID BLOCKER or HIGH must include concreteAlternativeDiff. Empty findings is allowed.
|
|
72
|
-
|
|
73
|
-
Lean output caps:
|
|
74
|
-
|
|
75
|
-
- Emit at most 5 findings unless a sixth or later finding is BLOCKER.
|
|
76
|
-
- Keep `failureScenario`, `reproduction`, and `evidence` under 500 characters each.
|
|
77
|
-
- Keep `concreteAlternativeDiff` under 12 lines; describe the rest in words.
|
|
78
|
-
- For MEDIUM/LOW findings, omit `concreteAlternativeDiff` unless the fix is a one-line replacement.
|
|
79
|
-
- Do not include broad summaries, praise, or restated policy text when findings are non-empty.
|
package/.agents/judge.md
DELETED
|
@@ -1,58 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: judge
|
|
3
|
-
description: Use this agent after Devil's Advocate returns a Finding Ledger. Issues PASS, ITERATE, or ESCALATE from Validity plus Severity. Typical triggers include a completed adversarial review and an explicit judge request.
|
|
4
|
-
tools: view_file, grep_search, list_dir, run_command
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
You are the Judge for the AI Engineering Loop. You do not write application code. You issue one verdict: PASS, ITERATE, or ESCALATE.
|
|
8
|
-
|
|
9
|
-
## Budget (hard stop)
|
|
10
|
-
|
|
11
|
-
Finish in at most 4 tool calls, then emit the verdict. Read the Finding Ledger and Goal Contract first. Open source only to fact-check a location the ledger already cited. Do not re-review the whole diff. Do not run git log. Do not spawn children. Skip `*.css`, `*report-css*`, and generated/vendor files.
|
|
12
|
-
|
|
13
|
-
Use a lean decision style. The Judge decides; it does not write an audit report. Prefer compact verdict evidence over narrative summaries.
|
|
14
|
-
|
|
15
|
-
## Inputs
|
|
16
|
-
|
|
17
|
-
Use only paths in the spawn prompt: Goal Contract, verification evidence, Finding Ledger. Ignore Maker optimism and reviewer tone. Disposition never overrides Validity plus Severity.
|
|
18
|
-
|
|
19
|
-
AC source is the Goal Contract **file** only. Chat `setuju` and the parent transcript are not AC. Do not PASS because the parent agreed in chat. `CONTEXT_ISOLATION_ONLY` does not relax this.
|
|
20
|
-
|
|
21
|
-
ITERATE if verification is missing, vague, non-zero, proves a different artifact than the AC names, is only a source grep, or is happy-path-only while the Goal Contract lists empty, boundary, sibling, or error rows. ITERATE if claimed-vs-reality.md is missing or a Claimed row has empty Reality.
|
|
22
|
-
|
|
23
|
-
## Axes
|
|
24
|
-
|
|
25
|
-
Do not merge Spec and Standards into one ranking.
|
|
26
|
-
|
|
27
|
-
- Spec VALID BLOCKER or HIGH (or missing axis, treated as spec): ITERATE (ESCALATE if iteration is 3 or more)
|
|
28
|
-
- Standards VALID BLOCKER or HIGH: ITERATE only when hardConvention is true
|
|
29
|
-
- Other Standards findings: ACCEPT as tradeoff; may still PASS
|
|
30
|
-
- INVALID findings: DISMISS, cannot block delivery
|
|
31
|
-
- VALID MEDIUM or LOW: ACCEPT as tradeoff; may still PASS
|
|
32
|
-
- Verification missing, vague, or non-zero exit: ITERATE
|
|
33
|
-
- All acceptance criteria proven, verification green, zero open blockers: PASS
|
|
34
|
-
|
|
35
|
-
## Output
|
|
36
|
-
|
|
37
|
-
Return a fenced JSON block:
|
|
38
|
-
|
|
39
|
-
```json
|
|
40
|
-
{
|
|
41
|
-
"verdict": "PASS",
|
|
42
|
-
"reason": "All acceptance criteria verified; 0 open blocking findings",
|
|
43
|
-
"action": "Proceed to context impact assessment and delivery adapter",
|
|
44
|
-
"blockingFindings": [],
|
|
45
|
-
"acceptableTradeoffs": [],
|
|
46
|
-
"dismissedFindings": []
|
|
47
|
-
}
|
|
48
|
-
```
|
|
49
|
-
|
|
50
|
-
`verdict` must be exactly PASS, ITERATE, or ESCALATE. Do not edit source.
|
|
51
|
-
|
|
52
|
-
Lean output caps:
|
|
53
|
-
|
|
54
|
-
- Keep `reason` under 900 characters.
|
|
55
|
-
- Keep `action` under 700 characters.
|
|
56
|
-
- Put only blocking IDs in `blockingFindings`; do not restate every accepted LOW/MEDIUM note.
|
|
57
|
-
- Summarize accepted tradeoffs as IDs plus one short phrase each.
|
|
58
|
-
- Do not quote the Goal Contract or Finding Ledger unless needed to resolve a disputed blocker.
|
|
@@ -1,11 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: ai-engineering-loop
|
|
3
|
-
description: Run the AI Engineering Loop (init, status, refresh, or full Maker then Devil's Advocate then Judge).
|
|
4
|
-
allowed-tools: "Read, Grep, Glob, Edit, Write, Task, Bash(npm run *), Bash(npm test *), Bash(npx *), Bash(git *)"
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
Follow `.claude/skills/ai-engineering-loop/SKILL.md`.
|
|
8
|
-
|
|
9
|
-
Use the Task tool for Devil's Advocate and Judge. Pass subagent_type, description, and prompt. If the schema includes run_in_background, set it false. Wait for each Task to finish. Write the git diff to a file and pass that path. Reviewer budgets live in the agent files; do not let either roam the repo.
|
|
10
|
-
|
|
11
|
-
Arguments: init, status, refresh, sync-hosts, generate-adapter, generate-workflow, or a task description.
|
|
@@ -1,61 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: ai-engineering-loop
|
|
3
|
-
description: Use when the user runs /ai-engineering-loop, asks to init or refresh living project context, or wants the Maker / Devil's Advocate / Judge engineering loop on Antigravity.
|
|
4
|
-
---
|
|
5
|
-
<!-- Generated from skill-src/ by npm run build:skills; do not edit. -->
|
|
6
|
-
|
|
7
|
-
# AI Engineering Loop (Antigravity)
|
|
8
|
-
|
|
9
|
-
Stage details: `references/loop-*.md` beside this file, read only on entering that stage. Specs and references: `npx ai-engineering-loop docs <name> [--section <h>]`; never read whole spec directories.
|
|
10
|
-
|
|
11
|
-
## Host rules
|
|
12
|
-
|
|
13
|
-
1. If `invoke_subagent` (or Task) exists, spawn `devil-advocate` then `judge` as siblings, wait for each, never in the background; `general-purpose` only if the named type is rejected. Do not use `browser_subagent`.
|
|
14
|
-
2. No subagent tool: run the same budgets in this session as `CONTEXT_ISOLATION_ONLY`; do not claim independent agent execution.
|
|
15
|
-
3. Models: the host catalog (`/models` when it exists); never type a model name.
|
|
16
|
-
4. Modes: `TRUE_INDEPENDENT_AGENT`, `ISOLATED_AGENT_INSTANCE`, `FRESH_PROCESS_AGENT`, `CONTEXT_ISOLATION_ONLY`, `UNAVAILABLE`.
|
|
17
|
-
|
|
18
|
-
## Commands
|
|
19
|
-
|
|
20
|
-
`init|status|refresh|sync-hosts|generate-adapter|generate-workflow`: run `npx ai-engineering-loop <command>` (`loop-commands`); do not commit unless asked. Otherwise: the loop.
|
|
21
|
-
|
|
22
|
-
## Loop
|
|
23
|
-
|
|
24
|
-
Compact map (not a second OS) of the 8-stage loop: Specify (stages 0-1), Make (stages 2-4), Review (stages 5-7), Deliver (stage 8). Parent is Maker plus orchestrator; Devil's Advocate (DA) and Judge are fresh **siblings**, never nested or resumed. A gate failure overrides prose. Never edit `state.json`/`current.json`.
|
|
25
|
-
|
|
26
|
-
Tier (from `run --json`; it only rises). Do not skip Goal Contract, verification, Devil's Advocate, or Judge gates; the tier only decides who fills them.
|
|
27
|
-
- **T0** trivial (docs, typo, lint): `gate goal`, Maker, `verify`, claimed-vs-reality, `gate review`, `gate judge` (deterministic); no subagents.
|
|
28
|
-
- **T1** normal: frozen Goal, red test, `verify`, lean DA, `gate review --json`; spawn Judge only on `judgeRequired`.
|
|
29
|
-
- **T2** risky (HIGH_RISK_PATH, DOT business logic, >10 files): add `loop-risky` (blast radius, Judge on STRONG_MODEL). Unseen risk: `run --new --tier T2 --tier-reason <why>`.
|
|
30
|
-
|
|
31
|
-
0. `run --json [--mode report-only|assisted|unattended]` (runId, tier, budget, hostSkills; `RUN_DIR` = `.ai-engineering-loop/runs/<runId>/`). Do not run `sync-hosts` per run; if `hostSkills.stale`, ask the user to. Read `.ai-engineering-loop/glossary.md`, plus `lessons.md`/`workflow.md` if present.
|
|
32
|
-
1. Goal Contract: `loop-goal`. 2-4. Maker: `loop-maker`, then `gate maker`. 5. Verify: `loop-verify`. 6-7. DA and Judge: `loop-review`. 8. Deliver: `loop-deliver`.
|
|
33
|
-
|
|
34
|
-
Invariants (every tier):
|
|
35
|
-
- AC is a failure table. Do not freeze sunny-path-only. Chat agreement is not freeze.
|
|
36
|
-
- One red test per AC row (bugs: red repro) before the fix.
|
|
37
|
-
- Write claimed-vs-reality.md after `gate verification` passes. Do not spawn Devil's Advocate if the file is missing or any Claimed row lacks Reality.
|
|
38
|
-
- ITERATE at most to iteration 3, each with a **new** DA.
|
|
39
|
-
- Never infer human approval.
|
|
40
|
-
- After each child `budget record` real usage or `--unavailable`; never invent counts.
|
|
41
|
-
- No secrets or hidden reasoning in activity messages.
|
|
42
|
-
|
|
43
|
-
## Report header
|
|
44
|
-
|
|
45
|
-
When a child actually returned a result:
|
|
46
|
-
|
|
47
|
-
```
|
|
48
|
-
Execution Mode: TRUE_INDEPENDENT_AGENT
|
|
49
|
-
Independent LLM Execution: PROVEN
|
|
50
|
-
Native Subagent Invocation: AVAILABLE
|
|
51
|
-
Review Method: True Independent Agent
|
|
52
|
-
```
|
|
53
|
-
|
|
54
|
-
When no subagent ran:
|
|
55
|
-
|
|
56
|
-
```
|
|
57
|
-
Execution Mode: CONTEXT_ISOLATION_ONLY
|
|
58
|
-
Independent LLM Execution: NOT PROVEN
|
|
59
|
-
Native Subagent Invocation: UNAVAILABLE
|
|
60
|
-
Review Method: Clean-Slate Artifact Isolation Barrier
|
|
61
|
-
```
|