@mutagent/evaluator 0.1.0-alpha.2 → 0.1.0-alpha.3
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.
|
@@ -29,8 +29,6 @@ metadata:
|
|
|
29
29
|
Evaluation-development-on-Tap for AI agents/skills. Invoke this skill to build a trustworthy
|
|
30
30
|
eval suite for a subject and run it to a GATE verdict.
|
|
31
31
|
|
|
32
|
-
> **DRAFT — NOT YET PUBLISHED.** Operator tags `evaluator-v*` only after real-run verification.
|
|
33
|
-
|
|
34
32
|
## §0 — Setup Detection (ALWAYS runs first)
|
|
35
33
|
|
|
36
34
|
> **CWD matters.** Every `scripts/cli/run.sh`-dispatched script MUST be invoked from the
|
package/README.md
CHANGED
|
@@ -1,7 +1,5 @@
|
|
|
1
1
|
# @mutagent/evaluator
|
|
2
2
|
|
|
3
|
-
> **DRAFT — NOT YET PUBLISHED.** Operator tags `evaluator-v*` only after real-run verification.
|
|
4
|
-
|
|
5
3
|
A **generic, subject-agnostic** AI-agent **auditor** — a **reviewer, never the
|
|
6
4
|
executor**. It verifies that a skill or agent did what it should, **repeatably**,
|
|
7
5
|
operator-out-of-loop, and emits a **4-tab master-audit report**.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@mutagent/evaluator",
|
|
3
|
-
"version": "0.1.0-alpha.
|
|
3
|
+
"version": "0.1.0-alpha.3",
|
|
4
4
|
"description": "mutagent-evaluator: a generic, subject-agnostic AI-agent auditor — reviewer, never executor. Audits any skill/agent against a generated subject profile and emits a 4-tab master-audit report.",
|
|
5
5
|
"license": "Apache-2.0",
|
|
6
6
|
"type": "module",
|