@dzhechkov/harness-cli 0.3.59 → 0.3.60
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/README.md +27 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -512,6 +512,33 @@ BTO benchmark: L0 Grade A (100%), L2 Opus weighted 7.58/10.
|
|
|
512
512
|
|
|
513
513
|
---
|
|
514
514
|
|
|
515
|
+
## Example: Import Skills from ECC
|
|
516
|
+
|
|
517
|
+
```bash
|
|
518
|
+
dz install @dzhechkov/skills-ecc # 20 curated ECC skills
|
|
519
|
+
dz import-ecc --limit 50 # import 50 from GitHub
|
|
520
|
+
dz import-ecc --local-path /path/to/ECC # from local clone (fast)
|
|
521
|
+
dz import-ecc --select docker-patterns,tdd # cherry-pick
|
|
522
|
+
```
|
|
523
|
+
|
|
524
|
+
## Example: Security Scan with AgentShield
|
|
525
|
+
|
|
526
|
+
```bash
|
|
527
|
+
# In Claude Code: "scan my agent config for security issues"
|
|
528
|
+
# → agentshield-scan skill activates (170 rules, 10 categories)
|
|
529
|
+
npx ecc-agentshield scan --format sarif # SARIF for GitHub Code Scanning
|
|
530
|
+
```
|
|
531
|
+
|
|
532
|
+
## Example: 4-Axis Risk Scoring
|
|
533
|
+
|
|
534
|
+
```bash
|
|
535
|
+
dz init --target codex --preset meta --enrich
|
|
536
|
+
# → agents/openai.yaml includes risk_level per skill
|
|
537
|
+
# Axes: base_tool + file_sensitivity + blast_radius + irreversibility
|
|
538
|
+
```
|
|
539
|
+
|
|
540
|
+
---
|
|
541
|
+
|
|
515
542
|
## Self-Learning: JSONL vs AgentDB
|
|
516
543
|
|
|
517
544
|
DZ Harness supports two memory backends for self-learning:
|
package/package.json
CHANGED