@ssheleg/agent-stack 0.13.2 → 0.13.3
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.
- package/CHANGELOG.md +8 -0
- package/README.md +21 -0
- package/package.json +1 -1
- package/plugins/agent-stack/.claude-plugin/plugin.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,13 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## v0.13.3 — public contract, measurable before it is marketable
|
|
4
|
+
|
|
5
|
+
The repository now opens with one install path and one concrete request, carries a
|
|
6
|
+
reviewable `SKILL-CARD.md`, portable trigger and behavior evals, and a generated
|
|
7
|
+
1200×630 social preview. CI runs the pinned family skill audit, validates the eval
|
|
8
|
+
schema, watches its planted defect fail, and checks the preview. The eval suite is
|
|
9
|
+
authored, not presented as a model result.
|
|
10
|
+
|
|
3
11
|
## v0.13.2 — the residue scan stops answering for other runs
|
|
4
12
|
|
|
5
13
|
`test/residue.py` now tags every workspace with the process group that made it, and the
|
package/README.md
CHANGED
|
@@ -1,5 +1,26 @@
|
|
|
1
1
|
# agent-stack
|
|
2
2
|
|
|
3
|
+
[](https://github.com/ssheleg/agent-stack/actions/workflows/validate.yml)
|
|
4
|
+
[](https://www.npmjs.com/package/@ssheleg/agent-stack)
|
|
5
|
+
[](LICENSE)
|
|
6
|
+
[](https://skills.sshlg.me/skills/agent-stack/)
|
|
7
|
+
|
|
8
|
+
**Build agent loops, harnesses, evals and protocol boundaries that stay inspectable under production failure.**
|
|
9
|
+
|
|
10
|
+
```bash
|
|
11
|
+
npx skills add ssheleg/agent-stack
|
|
12
|
+
```
|
|
13
|
+
|
|
14
|
+
Ask: `Design a resumable orchestrator with parallel collection and one convergence checker.`
|
|
15
|
+
|
|
16
|
+
**[Detailed docs →](https://skills.sshlg.me/skills/agent-stack/)**
|
|
17
|
+
|
|
18
|
+
**[Docs, and every skill →](https://skills.sshlg.me/)** · [this skill's page](https://skills.sshlg.me/skills/agent-stack/) · [follow @sshlg93 on X](https://x.com/intent/follow?screen_name=sshlg93)
|
|
19
|
+
|
|
20
|
+
Loads in **DeepSeek Harness** (`dsh`) with **no plugin to write**: it reads the
|
|
21
|
+
Agent Skills standard directly, scanning `~/.agents/skills` — where `npx skills
|
|
22
|
+
add` puts this pack — at rank 500.
|
|
23
|
+
|
|
3
24
|
Production patterns for building AI agent orchestrators — and for billing the
|
|
4
25
|
LLM access they burn.
|
|
5
26
|
|
package/package.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
"name": "agent-stack",
|
|
3
3
|
"displayName": "Agent Stack",
|
|
4
4
|
"description": "Two skills: agent-orchestrator — tool-calling loops, multi-stage pipelines with checkpoints, provider routing with fallback, four-layer memory, context engineering, plus the wallet side of reselling LLM access; and agent-evals — run/trace/thread evals, judges, and fixtures grown from production.",
|
|
5
|
-
"version": "0.13.
|
|
5
|
+
"version": "0.13.3",
|
|
6
6
|
"author": {
|
|
7
7
|
"name": "ssheleg",
|
|
8
8
|
"url": "https://x.com/sshlg93"
|