uv-suite 0.7.0 → 0.8.0
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/install.sh +18 -98
- package/package.json +1 -1
package/install.sh
CHANGED
|
@@ -221,9 +221,25 @@ Agent output is written to uv-out/. Agents read prior artifacts automatically:
|
|
|
221
221
|
|
|
222
222
|
${HOOKS_TEXT}
|
|
223
223
|
|
|
224
|
-
###
|
|
224
|
+
### Working practices
|
|
225
225
|
|
|
226
|
-
|
|
226
|
+
**Honesty:** If you can't find a doc, file, or function, say so explicitly. Never fabricate. Say: "I did not find X. What should I do?" Never invent facts to fill gaps. Calibrate confidence — use "I think" when unsure. If 2-3 attempts fail, stop and escalate with what you tried.
|
|
227
|
+
|
|
228
|
+
**Scope:** Do what was asked. Nothing more. No "while I'm here" fixes. If you notice something worth fixing, mention it at the end, don't silently change it.
|
|
229
|
+
|
|
230
|
+
**Destructive actions:** Always confirm before rm -rf, force push, dropping tables, modifying CI/CD, pushing to main.
|
|
231
|
+
|
|
232
|
+
**Completion:** "Done" means verified. Run the tests. Don't say "should work" when you could say "I ran it and it works."
|
|
233
|
+
|
|
234
|
+
**Failures:** When you fail, say so. Use the escalation format: what you tried, why each failed, your hypothesis, what you need.
|
|
235
|
+
|
|
236
|
+
**The user knows things you don't:** If something looks wrong, ask why before "fixing" it. Users have context you don't.
|
|
237
|
+
|
|
238
|
+
**Context:** If the conversation is long, suggest /compact or a new session. Past 90 min, suggest a break.
|
|
239
|
+
|
|
240
|
+
### Launching sessions
|
|
241
|
+
|
|
242
|
+
uv claude pro | uv codex pro | uv pro (shorthand)
|
|
227
243
|
EOF
|
|
228
244
|
|
|
229
245
|
echo " ✓ UV Suite section added to CLAUDE.md"
|
|
@@ -328,102 +344,6 @@ else
|
|
|
328
344
|
echo " Register manually after installing Claude Code: claude mcp add playwright -- npx @playwright/mcp@latest"
|
|
329
345
|
fi
|
|
330
346
|
|
|
331
|
-
# --- Write UV Suite context to CLAUDE.md ---
|
|
332
|
-
if [ "$INSTALL_MODE" = "project" ]; then
|
|
333
|
-
PROJECT_ROOT="$(dirname "$TARGET_DIR")"
|
|
334
|
-
CLAUDE_MD="$PROJECT_ROOT/CLAUDE.md"
|
|
335
|
-
|
|
336
|
-
# Check if UV Suite section already exists
|
|
337
|
-
if [ -f "$CLAUDE_MD" ] && grep -q "## UV Suite" "$CLAUDE_MD" 2>/dev/null; then
|
|
338
|
-
echo "Updating UV Suite section in CLAUDE.md..."
|
|
339
|
-
# Remove old UV Suite section and rewrite
|
|
340
|
-
sed -i.bak '/^## UV Suite$/,/^## [^U]/{ /^## [^U]/!d; }' "$CLAUDE_MD" 2>/dev/null || true
|
|
341
|
-
rm -f "$CLAUDE_MD.bak" 2>/dev/null
|
|
342
|
-
else
|
|
343
|
-
echo "Adding UV Suite section to CLAUDE.md..."
|
|
344
|
-
fi
|
|
345
|
-
|
|
346
|
-
cat >> "$CLAUDE_MD" << CLAUDEMD
|
|
347
|
-
|
|
348
|
-
## UV Suite
|
|
349
|
-
|
|
350
|
-
This project uses [UV Suite](https://github.com/utsavanand/uv-suite) for AI-assisted development.
|
|
351
|
-
|
|
352
|
-
**Active persona:** $PERSONA_LABEL
|
|
353
|
-
**Version:** $(cat "$UV_SUITE_DIR/package.json" 2>/dev/null | grep '"version"' | head -1 | sed 's/.*: "//;s/".*//')
|
|
354
|
-
|
|
355
|
-
### Available skills (slash commands)
|
|
356
|
-
|
|
357
|
-
| Command | Agent | What it does |
|
|
358
|
-
|---------|-------|-------------|
|
|
359
|
-
| /map-codebase [dir] | Cartographer | Build knowledge graph of codebase |
|
|
360
|
-
| /map-stack [dir] | Cartographer | Map multiple services and their connections |
|
|
361
|
-
| /spec [requirements] | Spec Writer | Write technical specification |
|
|
362
|
-
| /architect [spec] | Architect | Design architecture, decompose into Acts |
|
|
363
|
-
| /review | Reviewer | Code review (correctness, security, perf, slop) |
|
|
364
|
-
| /write-tests [file] | Test Writer | Generate tests matching project conventions |
|
|
365
|
-
| /write-evals [prompt] | Eval Writer | Write AI/LLM evaluation cases |
|
|
366
|
-
| /slop-check | Anti-Slop Guard | Detect 6 categories of AI-generated slop |
|
|
367
|
-
| /prototype [concept] | Prototype Builder | Build static React prototype |
|
|
368
|
-
| /security-review | Security Agent | OWASP audit, dependency scan, secret detection |
|
|
369
|
-
|
|
370
|
-
### Artifacts
|
|
371
|
-
|
|
372
|
-
All agent output is written to \`uv-out/\`. Each agent reads relevant prior artifacts from this directory automatically.
|
|
373
|
-
|
|
374
|
-
| Artifact | Written by | Read by |
|
|
375
|
-
|----------|-----------|---------|
|
|
376
|
-
| uv-out/map-codebase.md | /map-codebase | /architect, /review, /security-review |
|
|
377
|
-
| uv-out/specs/*.md | /spec | /architect, /write-tests, /write-evals |
|
|
378
|
-
| uv-out/architecture/*.md | /architect | /review, /write-tests, /slop-check |
|
|
379
|
-
| uv-out/review-*.md | /review | /slop-check, /security-review |
|
|
380
|
-
| uv-out/security-review-*.md | /security-review | — |
|
|
381
|
-
| uv-out/slop-check-*.md | /slop-check | — |
|
|
382
|
-
|
|
383
|
-
### Active hooks
|
|
384
|
-
|
|
385
|
-
Hooks fire automatically on every relevant action. You do not invoke these.
|
|
386
|
-
|
|
387
|
-
$(if [ "$PERSONA" = "professional" ]; then
|
|
388
|
-
cat << 'HOOKS'
|
|
389
|
-
- **auto-lint** (on file write) — runs prettier/ruff/gofmt
|
|
390
|
-
- **slop check** (on file write) — Haiku scans for obvious slop
|
|
391
|
-
- **danger zone** (on file edit) — warns if file is in DANGER-ZONES.md
|
|
392
|
-
- **destructive block** (on bash) — blocks rm -rf, force push
|
|
393
|
-
- **review reminder** (on session end) — reminds to /review if uncommitted changes
|
|
394
|
-
HOOKS
|
|
395
|
-
elif [ "$PERSONA" = "auto" ]; then
|
|
396
|
-
cat << 'HOOKS'
|
|
397
|
-
- **auto-lint** (on file write) — runs prettier/ruff/gofmt
|
|
398
|
-
- **destructive block** (on bash) — blocks rm -rf, force push
|
|
399
|
-
HOOKS
|
|
400
|
-
elif [ "$PERSONA" = "sport" ]; then
|
|
401
|
-
cat << 'HOOKS'
|
|
402
|
-
- **auto-lint** (on file write) — runs prettier/ruff/gofmt
|
|
403
|
-
HOOKS
|
|
404
|
-
elif [ "$PERSONA" = "spike" ]; then
|
|
405
|
-
cat << 'HOOKS'
|
|
406
|
-
- **doc slop check** (on file write) — Haiku checks documentation quality
|
|
407
|
-
HOOKS
|
|
408
|
-
fi)
|
|
409
|
-
|
|
410
|
-
### Context management
|
|
411
|
-
|
|
412
|
-
If the conversation is getting long, proactively suggest running /compact or starting a new session. Use /cost to check token usage. The user's status line shows context window usage.
|
|
413
|
-
|
|
414
|
-
### Launching sessions
|
|
415
|
-
|
|
416
|
-
\`\`\`
|
|
417
|
-
uv claude pro # Claude Code, Professional persona
|
|
418
|
-
uv claude auto # Claude Code, Auto persona
|
|
419
|
-
uv codex pro # OpenAI Codex, Professional persona
|
|
420
|
-
uv codex sport # OpenAI Codex, Sport persona
|
|
421
|
-
\`\`\`
|
|
422
|
-
CLAUDEMD
|
|
423
|
-
|
|
424
|
-
echo " ✓ UV Suite section added to CLAUDE.md"
|
|
425
|
-
fi
|
|
426
|
-
|
|
427
347
|
# --- Install launcher script ---
|
|
428
348
|
echo "Installing session launcher..."
|
|
429
349
|
cp "$UV_SUITE_DIR/uv.sh" "$TARGET_DIR/../uv.sh" 2>/dev/null || true
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "uv-suite",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.8.0",
|
|
4
4
|
"description": "Portable framework for AI-assisted software development. 10 agents, 9 skills, 5 hooks, 4 personas. Works with Claude Code, Cursor, and Codex.",
|
|
5
5
|
"author": "Utsav Anand",
|
|
6
6
|
"license": "MIT",
|