create-majlis 0.3.0 → 0.3.2

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.
Files changed (2) hide show
  1. package/dist/index.js +29 -15
  2. package/package.json +1 -1
package/dist/index.js CHANGED
@@ -114,13 +114,29 @@ Before building:
114
114
  3. Check docs/classification/ for problem taxonomy
115
115
  4. Check docs/experiments/ for prior work
116
116
 
117
- During building:
118
- - Create branch: exp/NNN-description
119
- - Create experiment log from template
117
+ ## Scope Constraint (CRITICAL)
118
+
119
+ You get ONE attempt per cycle. Your job is:
120
+ 1. Read and diagnose \u2014 understand the problem thoroughly
121
+ 2. Form ONE hypothesis about what to fix
122
+ 3. Implement ONE focused change (not a multi-step debug session)
123
+ 4. Run the benchmark ONCE to see the result
124
+ 5. Document what you did, what happened, and what you think the next step should be
125
+ 6. STOP
126
+
127
+ Do NOT iterate. Do NOT try multiple approaches. Do NOT debug your own fix.
128
+ If your change doesn't work, document why and let the cycle continue \u2014
129
+ the adversary, critic, and verifier will help diagnose what went wrong.
130
+ The cycle will come back to you with their insights.
131
+
132
+ If you find yourself wanting to "try one more thing," that's the signal to stop
133
+ and write up what you learned. The other agents exist precisely for this reason.
134
+
135
+ ## During building:
120
136
  - Tag EVERY decision: proof / test / strong-consensus / consensus / analogy / judgment
121
137
  - When making judgment-level decisions, state: "This is judgment \u2014 reasoning without precedent"
122
138
  - Run baseline metrics BEFORE making changes
123
- - Run comparison metrics AFTER making changes
139
+ - Run comparison metrics AFTER making changes (once)
124
140
 
125
141
  You may NOT verify your own work or mark your own decisions as proven.
126
142
  Output your decisions in structured format so they can be recorded in the database.
@@ -156,9 +172,8 @@ Rules:
156
172
  - Every doubt MUST reference evidence. "This feels wrong" is not a doubt.
157
173
  - You may NOT suggest fixes. Identify problems only.
158
174
  - Focus on judgment and analogy-level decisions first.
159
- - You may NOT modify any files. Produce a doubt document only.
160
-
161
- Write to docs/doubts/NNN-against-experiment-NNN.md
175
+ - You may NOT modify any files. Produce your doubt document as output only.
176
+ - Do NOT attempt to write files. The framework saves your output automatically.
162
177
 
163
178
  ## Structured Output Format
164
179
  <!-- majlis-json
@@ -184,9 +199,8 @@ For each approach the builder takes, ask:
184
199
  - Under what conditions do two things the builder treats as distinct become identical?
185
200
 
186
201
  Produce constructed counterexamples with reasoning.
187
- Do NOT suggest fixes. Do NOT modify files.
188
-
189
- Write to docs/challenges/NNN-against-experiment-NNN.md
202
+ Do NOT suggest fixes. Do NOT modify files. Do NOT attempt to write files.
203
+ The framework saves your output automatically.
190
204
 
191
205
  ## Structured Output Format
192
206
  <!-- majlis-json
@@ -216,7 +230,7 @@ CONTENT CHECK:
216
230
  Grade each component: sound / good / weak / rejected
217
231
  Grade each doubt/challenge: confirmed / dismissed (with evidence) / inconclusive
218
232
 
219
- Write to docs/verification/NNN-for-experiment-NNN.md
233
+ Produce your verification report as output. The framework saves it automatically.
220
234
 
221
235
  ## Structured Output Format
222
236
  <!-- majlis-json
@@ -250,7 +264,8 @@ Independently propose:
250
264
  Compare your decomposition with the existing classification.
251
265
  Flag structural divergences \u2014 these are the most valuable signals.
252
266
 
253
- Write to docs/reframes/NNN.md`,
267
+ Produce your reframe document as output. Do NOT attempt to write files.
268
+ The framework saves your output automatically.`,
254
269
  compressor: `---
255
270
  name: compressor
256
271
  model: opus
@@ -297,9 +312,8 @@ For the given experiment:
297
312
  Rules:
298
313
  - Present findings neutrally. Report each approach on its own terms.
299
314
  - Note where external approaches contradict the current one \u2014 these are the most valuable signals.
300
- - You may NOT modify code or make decisions. Produce a rihla document only.
301
-
302
- Write to docs/rihla/NNN-scout-for-experiment-NNN.md
315
+ - You may NOT modify code or make decisions. Produce your rihla document as output only.
316
+ - Do NOT attempt to write files. The framework saves your output automatically.
303
317
 
304
318
  ## Structured Output Format
305
319
  <!-- majlis-json
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "create-majlis",
3
- "version": "0.3.0",
3
+ "version": "0.3.2",
4
4
  "description": "Scaffold the Majlis Framework into a project",
5
5
  "bin": {
6
6
  "create-majlis": "./dist/index.js"