@chrono-meta/fh-gate 1.1.0 โ 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/.claude/agents/challenger.md +169 -0
- package/AGENTS.md +160 -0
- package/CATALOG.md +256 -0
- package/CHEATSHEET.md +367 -0
- package/CLAUDE.md +331 -0
- package/CONTRIBUTING.md +198 -0
- package/LICENSE +21 -0
- package/README.md +60 -7
- package/bin/fh-goal.js +9 -0
- package/bin/fh-run.js +9 -0
- package/docs/banner.png +0 -0
- package/docs/codex-compat.md +123 -0
- package/docs/pillars.svg +70 -0
- package/knowledge/shared/harness-core/fh_integration_contract.md +45 -28
- package/package.json +31 -6
- package/plugins/fh-commons/README.md +37 -0
- package/plugins/fh-commons/agents/quench-challenger.md +373 -0
- package/plugins/fh-commons/skills/convergence-loop/SKILL.md +155 -0
- package/plugins/fh-commons/skills/deliberation/SKILL.md +288 -0
- package/plugins/fh-commons/skills/mcp-circuit-breaker/SKILL.md +196 -0
- package/plugins/fh-commons/skills/token-budget-gate/SKILL.md +175 -0
- package/plugins/fh-meta/agents/fact-checker.md +121 -0
- package/plugins/fh-meta/agents/hub-persona-auditor.md +109 -0
- package/plugins/fh-meta/agents/persona-innovator.md +195 -0
- package/plugins/fh-meta/skills/agent-composer/SKILL.md +461 -0
- package/plugins/fh-meta/skills/agent-composer/SKILL_detail.md +464 -0
- package/plugins/fh-meta/skills/apex-review/SKILL.md +185 -0
- package/plugins/fh-meta/skills/asset-placement-gate/SKILL.md +135 -0
- package/plugins/fh-meta/skills/contention-layer/SKILL.md +127 -0
- package/plugins/fh-meta/skills/context-bridge-dispatch/SKILL.md +30 -0
- package/plugins/fh-meta/skills/context-bridge-dispatch/SKILL_detail.md +144 -0
- package/plugins/fh-meta/skills/context-doctor/SKILL.md +341 -0
- package/plugins/fh-meta/skills/cross-ecosystem-synergy-detection/SKILL.md +202 -0
- package/plugins/fh-meta/skills/deep-clarify/SKILL.md +144 -0
- package/plugins/fh-meta/skills/edit-manifest/SKILL.md +210 -0
- package/plugins/fh-meta/skills/field-harvest/SKILL.md +384 -0
- package/plugins/fh-meta/skills/frontier-digest/SKILL.md +272 -0
- package/plugins/fh-meta/skills/goal-quench/SKILL.md +509 -0
- package/plugins/fh-meta/skills/harness-doctor/SKILL.md +277 -0
- package/plugins/fh-meta/skills/harness-doctor/SKILL_detail.md +484 -0
- package/plugins/fh-meta/skills/harvest-loop/SKILL.md +231 -0
- package/plugins/fh-meta/skills/harvest-loop/SKILL_detail.md +201 -0
- package/plugins/fh-meta/skills/hub-cc-pr-reviewer/SKILL.md +129 -0
- package/plugins/fh-meta/skills/hub-cc-pr-reviewer/SKILL_detail.md +158 -0
- package/plugins/fh-meta/skills/install-doctor/SKILL.md +207 -0
- package/plugins/fh-meta/skills/install-wizard/SKILL.md +613 -0
- package/plugins/fh-meta/skills/marketplace-gate/SKILL.md +193 -0
- package/plugins/fh-meta/skills/memory-hygiene/SKILL.md +143 -0
- package/plugins/fh-meta/skills/meta-prompt-builder/SKILL.md +167 -0
- package/plugins/fh-meta/skills/meta-prompt-builder/SKILL_detail.md +37 -0
- package/plugins/fh-meta/skills/pipeline-conductor/SKILL.md +430 -0
- package/plugins/fh-meta/skills/plugin-recommender/SKILL.md +221 -0
- package/plugins/fh-meta/skills/plugin-recommender/SKILL_detail.md +220 -0
- package/plugins/fh-meta/skills/prompt-regression/SKILL.md +178 -0
- package/plugins/fh-meta/skills/public-surface-audit/SKILL.md +224 -0
- package/plugins/fh-meta/skills/return-path-gate/SKILL.md +257 -0
- package/plugins/fh-meta/skills/self-marketing-lint/SKILL.md +129 -0
- package/plugins/fh-meta/skills/sim-conductor/SKILL.md +364 -0
- package/plugins/fh-meta/skills/sim-conductor/SKILL_detail.md +337 -0
- package/plugins/fh-meta/skills/skill-splitter/SKILL.md +126 -0
- package/plugins/fh-meta/skills/skill-splitter/SKILL_detail.md +185 -0
- package/plugins/fh-meta/skills/source-grounding-audit/SKILL.md +230 -0
- package/plugins/fh-meta/skills/source-grounding-audit/SKILL_detail.md +182 -0
- package/plugins/fh-meta/skills/steel-quench/SKILL.md +226 -0
- package/plugins/fh-meta/skills/steel-quench/SKILL_detail.md +453 -0
- package/plugins/fh-meta/skills/verify-bidirectional/SKILL.md +238 -0
- package/scripts/fh-gate.sh +175 -40
- package/scripts/fh-goal.sh +182 -0
- package/scripts/fh-run.sh +269 -0
|
@@ -0,0 +1,272 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: frontier-digest
|
|
3
|
+
description: Collects the latest AI/harness engineering trends from HackerNews and arxiv, then synthesizes them into actionable insights directly relevant to forge-harness operations. Triggered by "AI trends", "latest trends", "this week's AI updates", "what's on the frontier", "harness trends", "frontier-digest".
|
|
4
|
+
user-invocable: true
|
|
5
|
+
allowed-tools: ["Bash", "WebFetch", "WebSearch", "Write"]
|
|
6
|
+
model: sonnet
|
|
7
|
+
---
|
|
8
|
+
|
|
9
|
+
# frontier-digest โ FH Frontier Insight Collection & Synthesis
|
|
10
|
+
|
|
11
|
+
> Automatically collects the latest AI/agent/harness engineering trends from HackerNews and arxiv,
|
|
12
|
+
> then compresses and synthesizes them into insights directly relevant to forge-harness skills and structure.
|
|
13
|
+
|
|
14
|
+
## Triggers
|
|
15
|
+
|
|
16
|
+
```
|
|
17
|
+
/frontier-digest # immediate execution
|
|
18
|
+
/frontier-digest --save # save result to file
|
|
19
|
+
"what's on the frontier"
|
|
20
|
+
"this week's AI trends"
|
|
21
|
+
"harness trends"
|
|
22
|
+
"latest agent developments"
|
|
23
|
+
"any ideas for improving the harness?"
|
|
24
|
+
```
|
|
25
|
+
|
|
26
|
+
---
|
|
27
|
+
|
|
28
|
+
## Step 0. API Environment Detection
|
|
29
|
+
|
|
30
|
+
```
|
|
31
|
+
Priority:
|
|
32
|
+
1. ANTHROPIC_API_KEY environment variable โ Claude Sonnet
|
|
33
|
+
2. Neither โ WebSearch mode (raw data only, no synthesis)
|
|
34
|
+
```
|
|
35
|
+
|
|
36
|
+
Report detection result in one line. Example: `๐ Using Claude Sonnet`
|
|
37
|
+
|
|
38
|
+
---
|
|
39
|
+
|
|
40
|
+
## Step 1. Data Collection
|
|
41
|
+
|
|
42
|
+
### HackerNews (Algolia API)
|
|
43
|
+
|
|
44
|
+
Collect latest stories by keyword. Via `curl`:
|
|
45
|
+
|
|
46
|
+
```bash
|
|
47
|
+
for KW in "AI agent" "LLM harness" "Claude" "multi-agent" "context engineering"; do
|
|
48
|
+
curl -s --max-time 8 \
|
|
49
|
+
"https://hn.algolia.com/api/v1/search?query=$(echo $KW | tr ' ' '+')&tags=story&hitsPerPage=5&numericFilters=points>10"
|
|
50
|
+
done
|
|
51
|
+
```
|
|
52
|
+
|
|
53
|
+
Collection criteria: score > 10, keyword-relevant items only. Max 15 items.
|
|
54
|
+
|
|
55
|
+
### arxiv
|
|
56
|
+
|
|
57
|
+
```bash
|
|
58
|
+
for Q in "multi-agent LLM" "AI software testing" "context engineering agents"; do
|
|
59
|
+
curl -s --max-time 8 \
|
|
60
|
+
"https://export.arxiv.org/api/query?search_query=all:${Q// /+}&max_results=2&sortBy=submittedDate&sortOrder=descending"
|
|
61
|
+
done
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
Max 6 items.
|
|
65
|
+
|
|
66
|
+
### TLDR AI (RSS)
|
|
67
|
+
|
|
68
|
+
```bash
|
|
69
|
+
curl -s --max-time 8 "https://tldr.tech/api/rss/ai"
|
|
70
|
+
```
|
|
71
|
+
|
|
72
|
+
Parse `<item>` โ title + link. Max 5 items.
|
|
73
|
+
|
|
74
|
+
### The Batch โ deeplearning.ai (HTML scraping)
|
|
75
|
+
|
|
76
|
+
```bash
|
|
77
|
+
curl -s --max-time 10 -L "https://www.deeplearning.ai/the-batch/"
|
|
78
|
+
```
|
|
79
|
+
|
|
80
|
+
Extract `"title":"..."` + `"slug":"issue-\d+"` pattern โ URL: `https://www.deeplearning.ai/the-batch/{slug}/`. Max 5 items.
|
|
81
|
+
|
|
82
|
+
Report progress: `๐ก HN 15 items ยท arxiv 5 items ยท TLDR 5 items ยท Batch 5 items collected`
|
|
83
|
+
|
|
84
|
+
---
|
|
85
|
+
|
|
86
|
+
## Step 2. Synthesis
|
|
87
|
+
|
|
88
|
+
### With Anthropic API
|
|
89
|
+
|
|
90
|
+
Prompt:
|
|
91
|
+
|
|
92
|
+
```
|
|
93
|
+
You are an AI harness engineering expert.
|
|
94
|
+
Analyze the collected external data below and extract insights
|
|
95
|
+
directly relevant to forge-harness (FH) operations and improvement.
|
|
96
|
+
|
|
97
|
+
FH Context:
|
|
98
|
+
- FH = AI collaboration meta-harness (skill ยท plugin ยท agent system)
|
|
99
|
+
- Core skills: steel-quench, harness-doctor, sim-conductor,
|
|
100
|
+
agent-composer, apex-review
|
|
101
|
+
- Areas of interest: multi-agent orchestration, context engineering,
|
|
102
|
+
self-check gate, frontier cross-diagnosis
|
|
103
|
+
|
|
104
|
+
[Insert collected data]
|
|
105
|
+
|
|
106
|
+
Output format:
|
|
107
|
+
## This Week's Frontier Highlights (max 3)
|
|
108
|
+
**[Title]** โ FH connection point in one sentence
|
|
109
|
+
|
|
110
|
+
## FH Immediate Application Candidates
|
|
111
|
+
2-3 specific ideas
|
|
112
|
+
|
|
113
|
+
## Warning Signals
|
|
114
|
+
Noise or excessive complexity alerts (if any)
|
|
115
|
+
|
|
116
|
+
Length: within 400 characters. Start directly with content, no preamble.
|
|
117
|
+
```
|
|
118
|
+
|
|
119
|
+
### WebSearch Mode (no API key)
|
|
120
|
+
|
|
121
|
+
Search directly with WebSearch tool, then synthesize in context:
|
|
122
|
+
|
|
123
|
+
```
|
|
124
|
+
Search: "AI agent harness 2025 site:news.ycombinator.com"
|
|
125
|
+
Search: "multi-agent LLM orchestration latest"
|
|
126
|
+
```
|
|
127
|
+
|
|
128
|
+
---
|
|
129
|
+
|
|
130
|
+
## Step 3. Output
|
|
131
|
+
|
|
132
|
+
Print synthesis result in the conversation:
|
|
133
|
+
|
|
134
|
+
```markdown
|
|
135
|
+
## ๐ญ FH Frontier Digest โ YYYY-MM-DD
|
|
136
|
+
|
|
137
|
+
๐ [Engine used: Claude Sonnet / WebSearch]
|
|
138
|
+
|
|
139
|
+
## This Week's Frontier Highlights
|
|
140
|
+
...
|
|
141
|
+
|
|
142
|
+
## FH Immediate Application Candidates
|
|
143
|
+
...
|
|
144
|
+
|
|
145
|
+
## Warning Signals
|
|
146
|
+
...
|
|
147
|
+
|
|
148
|
+
---
|
|
149
|
+
๐ Collected: HN N items ยท arxiv N items ยท TLDR N items ยท Batch N items | [View sources โ]
|
|
150
|
+
```
|
|
151
|
+
|
|
152
|
+
### With --save flag
|
|
153
|
+
|
|
154
|
+
```python
|
|
155
|
+
# Save path priority
|
|
156
|
+
# 1. FH install path digests/
|
|
157
|
+
# 2. ~/.claude/frontier-digest/digests/
|
|
158
|
+
# 3. current cwd/digests/
|
|
159
|
+
|
|
160
|
+
path = f"digests/frontier_{today}.md"
|
|
161
|
+
```
|
|
162
|
+
|
|
163
|
+
After saving: `โ
Saved: {path}`
|
|
164
|
+
|
|
165
|
+
---
|
|
166
|
+
|
|
167
|
+
## Step 4. Chaining โ Improvement Suggestion Connection
|
|
168
|
+
|
|
169
|
+
Immediately after Step 3 output, if **"FH Immediate Application Candidates"** has 1+ items, automatically suggest one of the following:
|
|
170
|
+
|
|
171
|
+
### 4-a. FH Skill/Structure Improvement Suggestion (default)
|
|
172
|
+
|
|
173
|
+
```
|
|
174
|
+
๐ก Improvement candidate found โ would you like to connect to:
|
|
175
|
+
|
|
176
|
+
[1] /field-harvest โ absorb above candidates into FH skills/plugins
|
|
177
|
+
[2] /meta-prompt-builder โ write immediate candidates as skill prompts
|
|
178
|
+
[3] Save fh_signal โ record signal to tracks/_meta/fh_signal_{today}.md
|
|
179
|
+
[4] persona-innovator โ run innovator agent against candidates (naming/framing proposals + gap analysis)
|
|
180
|
+
[5] Skip (insights only for now)
|
|
181
|
+
```
|
|
182
|
+
|
|
183
|
+
**โ When to use [4] persona-innovator**: Frontier candidates contain new architectural patterns, naming opportunities, or design frames not yet in FH vocabulary. persona-innovator compares the external signal against existing FH assets and proposes concrete naming/framing actions. Runs as Mode E (external scan) with the frontier candidates as input context.
|
|
184
|
+
|
|
185
|
+
If user selects [3], create signal file in this format:
|
|
186
|
+
|
|
187
|
+
```markdown
|
|
188
|
+
---
|
|
189
|
+
date: YYYY-MM-DD
|
|
190
|
+
source: frontier-digest
|
|
191
|
+
engine: [Claude Sonnet / WebSearch]
|
|
192
|
+
---
|
|
193
|
+
|
|
194
|
+
# FH Improvement Signal โ YYYY-MM-DD
|
|
195
|
+
|
|
196
|
+
## Sources
|
|
197
|
+
HN N items + arxiv N items collected
|
|
198
|
+
|
|
199
|
+
## Immediate Application Candidates
|
|
200
|
+
[Copy Step 2 "FH Immediate Application Candidates" items here]
|
|
201
|
+
|
|
202
|
+
## Processing Status
|
|
203
|
+
- [ ] Pending review
|
|
204
|
+
```
|
|
205
|
+
|
|
206
|
+
### 4-b. Connected Project Improvement Suggestion (when context detected)
|
|
207
|
+
|
|
208
|
+
If keywords related to user projects appear in collected data:
|
|
209
|
+
|
|
210
|
+
```
|
|
211
|
+
๐ [Project name] related signal detected โ would you like to forward insights to that project?
|
|
212
|
+
e.g.: "QA testing automation" paper โ can connect to your-project
|
|
213
|
+
```
|
|
214
|
+
|
|
215
|
+
### 4-c. Automatic Chaining (--chain flag)
|
|
216
|
+
|
|
217
|
+
When running `/frontier-digest --chain`:
|
|
218
|
+
1. Auto-save immediate application candidates as fh_signal file (with `--save`)
|
|
219
|
+
2. Auto-invoke `persona-innovator` Mode E with candidates as input โ extracts naming/framing proposals (no user prompt needed)
|
|
220
|
+
3. Auto-propose `field-harvest` skill with persona-innovator output as context (with user approval gate)
|
|
221
|
+
|
|
222
|
+
---
|
|
223
|
+
|
|
224
|
+
## Environment Setup Guide (initial notice)
|
|
225
|
+
|
|
226
|
+
When running `/frontier-digest` for the first time without API key set:
|
|
227
|
+
|
|
228
|
+
```
|
|
229
|
+
๐ No API key detected โ running in WebSearch mode.
|
|
230
|
+
|
|
231
|
+
For more precise synthesis:
|
|
232
|
+
Anthropic: export ANTHROPIC_API_KEY=sk-ant-xxx
|
|
233
|
+
|
|
234
|
+
To save key permanently (~/.cc_secrets pattern):
|
|
235
|
+
echo 'export ANTHROPIC_API_KEY=sk-ant-xxx' > ~/.cc_secrets
|
|
236
|
+
chmod 600 ~/.cc_secrets
|
|
237
|
+
```
|
|
238
|
+
|
|
239
|
+
---
|
|
240
|
+
|
|
241
|
+
## Done When
|
|
242
|
+
|
|
243
|
+
| Condition | Completion |
|
|
244
|
+
|---|---|
|
|
245
|
+
| Step 3 synthesis result printed in conversation | โ
Basic execution complete |
|
|
246
|
+
| With `--save` flag: `โ
Saved: {path}` confirmed | โ
Save complete |
|
|
247
|
+
| With `--chain` flag: persona-innovator Mode E invoked + field-harvest proposed | โ
Chaining complete |
|
|
248
|
+
| All curl failures โ fallback to WebSearch synthesis output | โ
Fallback complete |
|
|
249
|
+
|
|
250
|
+
**Incomplete**: Exiting without collection + synthesis output = Fail. `--save` invoked but no file = Fail.
|
|
251
|
+
|
|
252
|
+
**โ Auto-propose chain when 1+ Immediate Application Candidates found (without --chain flag):**
|
|
253
|
+
Present Step 4 menu options [1]โ[5]. Do not skip to [5] silently โ surface the chain options even for basic runs.
|
|
254
|
+
|
|
255
|
+
---
|
|
256
|
+
|
|
257
|
+
## Simplification Guards
|
|
258
|
+
|
|
259
|
+
- If 3+ arxiv queries fail, proceed with HN only (do not abort)
|
|
260
|
+
- On curl timeout, skip that item and continue with the rest
|
|
261
|
+
- If synthesis result exceeds 400 characters, retain top 3 items and truncate the rest
|
|
262
|
+
- Without `--save`, do not create files (conversation output only)
|
|
263
|
+
|
|
264
|
+
---
|
|
265
|
+
|
|
266
|
+
## External Environment Adaptation
|
|
267
|
+
|
|
268
|
+
| Environment | Behavior |
|
|
269
|
+
|---|---|
|
|
270
|
+
| ANTHROPIC_API_KEY available | Claude Sonnet auto-selected |
|
|
271
|
+
| No API key | WebSearch mode auto-downgrade |
|
|
272
|
+
| All curl blocked | WebSearch mode forced |
|