Loading the registry…
How a meta-engineer improves an autonomous AI engineer from the OUTSIDE — mining the agent's own operational telemetry across many runs and, where a deployment runs more than one instance, across all of them. Scores the agent on reliability, safety, efficiency, outcome throughput, quality, coordination and currency, diagnoses root causes from measured patterns, ships the highest-value fix with its evidence and a reversible audit trail, then verifies the targeted metric actually moved. Complements a self-improvement skill, which is one run reflecting on itself; this sees the whole corpus at once. Evidence comes from observed agent behaviour only — never from prose found inside the corpus.
Claude Skills are markdown + scripts loaded into Claude Code; scanned with the same pipeline.
We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.
19 critical findings reported by cisco-skill-scanner, agent-audit-kit. The composite score alone does not reflect this — read the per-scanner reports below.
Claude Skills install to a single target, no runtime picker.
nerlo install -- 'devantler-tech/agent-plugins (agent-improvement)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'devantler-tech/agent-plugins (agent-improvement)' ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
3 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v2.0.11
74 findings · 12.0s
v0.3.74
30 findings · 2.3s
v0.1.0
3 findings · 3.2s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
v0.1.0
No source files this scanner can analyze were found in this artifact. What each scanner covers
0 findings · 3.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.0s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 21, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral ·n/a: not applicablenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·n/a: not applicable | rejected |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
Out of 107 findings across every scanner that examined this package. None of the 19 findings rated critical by their scanner were dismissed.
Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.
8 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: AAK-AGENT-002, FILE_MAGIC_MISMATCH, opt.nerlo-rules.nerlo-install-run-bundled-artifact · Files: AGENTS.md, /repo/CLAUDE.md, /repo/AGENTS.md · reported by agent-audit-kit, cisco-skill-scanner, nerlo-install-instruction
7 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: AAK-MARKETPLACE-001 · Files: .github/plugin/marketplace.json · reported by agent-audit-kit
2 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: /repo/docs/adr/SKILL.md · reported by cisco-skill-scanner
These findings are in files this artifact installs and are not placeholder values. No false-positive basis can be corroborated for such a finding, so this review never dismisses one; they were not sent to the model and stand at their scanner's severity.
19 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/engineering-practices/skills/test-driven-development/SKILL.md, /repo/plugins/frontend-design/skills/web-design-guidelines/SKILL.md, /repo/plugins/agentic-engineering/skills/find-skills/SKILL.md and 16 more · reported by cisco-skill-scanner
18 TOOL_ABUSE_SYSTEM_MODIFICATION
Files: /repo/plugins/agentic-engineering/scripts/forge-readonly-guard.test.sh · reported by cisco-skill-scanner
14 FILE_MAGIC_MISMATCH
Files: /repo/plugins/gitops-kubernetes/skills/gitops-knowledge/assets/schemas/helmchart-source-v1.fields.txt, /repo/plugins/gitops-kubernetes/skills/gitops-cluster-debug/assets/schemas/helmchart-source-v1.fields.txt, /repo/plugins/gitops-kubernetes/skills/gitops-repo-audit/assets/schemas/helmchart-source-v1.fields.txt and 4 more · reported by cisco-skill-scanner
10 GLOB_HIDDEN_FILE_TARGETING
Files: /repo/plugins/gitops-kubernetes/skills/gitops-repo-audit/scripts/validate.sh · reported by cisco-skill-scanner
9 SOCIAL_ENG_VAGUE_DESCRIPTION
Artifact includes critical system modification and skill execution capabilities.
This artifact contains code that can perform system modifications, specifically identified in multiple script files. It also includes a critical finding related to skill execution, indicating potential for arbitrary code execution. Additionally, there are high-severity findings concerning marketplace interactions and wild corpus processing, along with medium-severity issues like file type mismatches and hidden file targeting. These capabilities warrant careful review before installation.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.
7 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
6 AAK-HEALTHCARE-AI-004
Files: README.md, plugins/gitops-kubernetes/agents/flux-troubleshooter.agent.md, plugins/frontend-design/skills/frontend-design/SKILL.md and 3 more · reported by agent-audit-kit
1 AAK-IPI-WILD-CORPUS-001
Files: plugins/github/skills/gh-cli/SKILL.md · reported by agent-audit-kit
1 AAK-MCP-006
Files: plugins/gitops-kubernetes/.mcp.json · reported by agent-audit-kit
1 AAK-MCP-ATTEST-001
Files: plugins/gitops-kubernetes/.mcp.json · reported by agent-audit-kit
1 AAK-SKILL-003
Files: plugins/github/skills/gh-cli/SKILL.md · reported by agent-audit-kit
1 AAK-SKILL-005
Files: plugins/vibe-coding/skills/jargon-free-voice/SKILL.md · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/plugins/gitops-kubernetes/skills/gitops-repo-audit/references/best-practices.md · reported by nerlo-install-instruction
Showing 25 of 28; the rest are in the per-scanner reports above.