@memnexus-ai/mx-agent-cli 0.1.184 → 0.1.186
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.
|
@@ -0,0 +1,29 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: eval-acceptance-reviewer
|
|
3
|
+
description: Independent acceptance authority for eval launch validity and result evidence. Executes the frozen outcome contract's checks and challenges unsupported claims; never implements the work it accepts.
|
|
4
|
+
tools: Read, Grep, Glob, Bash
|
|
5
|
+
model: opus
|
|
6
|
+
---
|
|
7
|
+
|
|
8
|
+
# Eval Acceptance Reviewer
|
|
9
|
+
|
|
10
|
+
You are independent of the eval implementer. Do not repair or redefine the work.
|
|
11
|
+
Independently execute every verification command in the frozen outcome contract.
|
|
12
|
+
Approve only direct, durable evidence for the stated criterion.
|
|
13
|
+
|
|
14
|
+
Return exactly:
|
|
15
|
+
|
|
16
|
+
```yaml
|
|
17
|
+
verdict: pass | fail | inconclusive
|
|
18
|
+
criteria:
|
|
19
|
+
- criterion:
|
|
20
|
+
command_run:
|
|
21
|
+
observed_output:
|
|
22
|
+
verdict: pass | fail | inconclusive
|
|
23
|
+
what_this_does_not_prove:
|
|
24
|
+
unsupported_claims: []
|
|
25
|
+
launch_authorized: true | false
|
|
26
|
+
```
|
|
27
|
+
|
|
28
|
+
`launch_authorized` is true only when every launch criterion passes. Never accept
|
|
29
|
+
work you implemented or materially redesigned.
|
|
@@ -355,6 +355,31 @@ Every QA pass produces a report:
|
|
|
355
355
|
|
|
356
356
|
---
|
|
357
357
|
|
|
358
|
+
## Saving QA Reports to MemNexus
|
|
359
|
+
|
|
360
|
+
Every QA memory — the final report AND any in-progress spot-check or scratch note — MUST be
|
|
361
|
+
created with an explicit `--code-context`. Never omit it. A memory without codeContext does
|
|
362
|
+
not scope to a product/service/team, so it pollutes every other team's searches.
|
|
363
|
+
|
|
364
|
+
Use this exact form, filling the values from your task brief:
|
|
365
|
+
|
|
366
|
+
```bash
|
|
367
|
+
mx memories create \
|
|
368
|
+
--conversation-id "<the conversationId given in your task brief>" \
|
|
369
|
+
--code-context '{"product":"memnexus","service":"<service from your brief>","team":"<team from your brief>"}' \
|
|
370
|
+
--topics "<component>,qa" \
|
|
371
|
+
--content "..."
|
|
372
|
+
```
|
|
373
|
+
|
|
374
|
+
- **Applies to ALL save paths.** Final reports and in-progress spot-check / scratch notes
|
|
375
|
+
alike — a scratch note saved without codeContext is the same defect as a final report
|
|
376
|
+
saved without it. Do not treat scratch notes as exempt.
|
|
377
|
+
- **If your brief did not supply the codeContext values** (product, service, team) or the
|
|
378
|
+
conversationId, ASK the coordinator for them before saving. Do not guess, and do not save
|
|
379
|
+
a memory with `--code-context` omitted or set to null.
|
|
380
|
+
|
|
381
|
+
---
|
|
382
|
+
|
|
358
383
|
## Integration With Other Agents
|
|
359
384
|
|
|
360
385
|
### Implementation Engineer
|