Loading the registry…
Use PROACTIVELY whenever the user wants to understand, audit, map, survey, or document an existing codebase WITHOUT changing its code. Five-phase pipeline: Scope → Discover → Analyze → Synthesize → Report. State in the analysis file frontmatter (scoped → discovered → analyzed → synthesized → reported). Output is stored repo-local (external vault via `A1_VAULT_ROOT`, e.g. Obsidian): projects/<slug>/analyses/<YYYY-MM-DD>-<focus>[-N].md. Five focus modes: general, security, architecture, quality, onboarding. MUST trigger on: "analyze <project>" (alias: "analysiere <projekt>"), "project audit" (alias: "projekt-audit"), "codebase overview" (alias: "codebase-überblick"), "codebase scan", "security analysis" (alias: "security-analyse"), "security audit", "architecture analysis" (alias: "architektur-analyse"), "architecture review", "quality check for <project>" (alias: "quality-check für <projekt>"), "scan the tech stack" (alias: "tech-stack scannen"), "onboarding docs for <project>" (alias: "onboarding-doku für <projekt>"), "pre-refactor-audit", "how is <project> structured" (alias: "wie ist <projekt> aufgebaut"), "what runs in <project>" (alias: "was läuft in <projekt>"), or "a1-analyze". Orchestrates read-only sub-agents (a1-reinhard-reviewer, a1-alex-architekt, a1-marco-mapper, a1-walter-web-developer, a1-aik-ai-engineer, a1-ludwig-legal) in parallel during Phase 3, plus two always-on read-only lanes on every run: the code-simplifier agent (report-only) and the security-review lane owned by the a1-samuel-security agent. Writes a mandatory self-learning Retro to the learning store (repo-local default; external vault via `A1_VAULT_ROOT`, e.g. Obsidian) after every run (feeds a1-evolve). Never modifies project code; findings only. Do NOT activate for: bug reports (→ a1-fix), new feature work (→ a1-new-feature), PR code review (→ a1-reinhard-reviewer directly), or spec-vs-plan drift (→ a1-checklist checks #9/#10 for FR-coverage, a1-reconcile for spec-vs-implementation).
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.
64 critical findings reported by cisco-skill-scanner. 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 -- 'n3ural-a1/a1-specforge (a1-analyze)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'n3ural-a1/a1-specforge (a1-analyze)' ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
4 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
595 findings · 23.8s
v0.3.74
4 findings · 5.9s
v0.1.0
0 findings · 8.9s
v0.1.0
195 findings · 8.9s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.2s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image, nerlo-multi-source.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 16, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·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.
This review has not run for this scan yet. It runs once per scan, in the background, and is kept; it appears here when it has. Until then all 794 findings above stand exactly as their scanners reported them, at full severity.