Peaky8linders

Peaky8linders/claude-cortex

Hook

Runs when a session starts on startup and resume, executing on-session-start.sh via bash. From Peaky8linders/claude-cortex.

Peaky8linders/claude-cortex

Hook

Runs after a tool call finishes for Write, Edit, MultiEdit, Bash, Read and Search tool calls, executing on-tool-use.sh via bash (3 commands). From Peaky8linders/claude-cortex.

Peaky8linders/claude-cortex

Hook

Runs before the context is compacted for auto and manual tool calls, executing on-pre-compact.sh via bash. From Peaky8linders/claude-cortex.

Peaky8linders/claude-cortex

Hook

Runs after the context is compacted, executing on-post-compact.sh via bash. From Peaky8linders/claude-cortex.

Peaky8linders/claude-cortex

Hook

Runs when the agent finishes a response, executing on-stop.sh via bash. From Peaky8linders/claude-cortex.

Peaky8linders/specter-oss

Plugin Claude Code

Specter — EU AI Act compliance toolkit. Validate citations against the canonical 113-article + 13-annex catalog, query the four-axis agentic compound-risk taxonomy, look up role obligations, and run the LLM-as-Judge reward-hack detector on proposed remediation tasks.

Peaky8linders/specter-oss

Instructions file

Claude Code instructions for Peaky8linders/specter-oss, covering claude.md — specter-oss, what this project is, layout, hard rules (do not break) and conventions.

Peaky8linders/specter-oss

Plugin Claude Code

EU AI Act compliance toolkit for Claude Code — validate citations against the canonical 113-article + 13-annex catalog, query the four-axis agentic compound-risk taxonomy, look up role obligations, and run the LLM-as-Judge reward-hack detector on proposed remediation tasks. Wraps the specter Python package as a local.

Peaky8linders/specter-oss

MCP server Claude CodeCodexCursor +2

MCP server "specter" as configured in Peaky8linders/specter-oss. Runs specter.mcp_server with python.

Peaky8linders/specter-oss

Command

Validate an EU AI Act article reference against the canonical 113-article + 13-annex catalog.

Peaky8linders/specter-oss

Command

Convert internal Art. X(Y)(Z) / Annex IV(N) into publication form Article X.Y.Z / Annex IV.N.

Peaky8linders/specter-oss

Command

Run a proposal through the LLM-as-Judge ComplianceRewardHackDetector (6 checks).

Peaky8linders/specter-oss

Command

Return the canonical EU AI Act surface — 113 articles + 13 annexes.

Peaky8linders/specter-oss

Command

Return EU AI Act articles applicable to an operator role (provider / deployer / importer / distributor / etc.).

Peaky8linders/specter-oss

Command

Return the four-axis agentic-AI compound-risk taxonomy (cascading / emergent / attribution / temporal).

Peaky8linders/eu-ai-act-scanner

MCP server Claude CodeCodexCursor +2

MCP server "eu-ai-act-scanner" as configured in Peaky8linders/eu-ai-act-scanner. Launched with eu-ai-act-scan-mcp.

Peaky8linders/eu-ai-act-scanner

Command

Show which analyzers, compliance dimensions, and current findings in this codebase map to a specific EU AI Act article.

Peaky8linders/eu-ai-act-scanner

Command

Answer an EU AI Act question grounded in the bundled knowledge base — verbatim statute text, obligation paraphrases, and the compound-risk taxonomy. Offline and deterministic by default; cites the articles it relies on.

Peaky8linders/eu-ai-act-scanner

Command

Show real-world and research-demonstrated security incidents that map to a scanner dimension, EU AI Act article, or threat category. Surfaces OWASP LLM/ASI, NIST AI RMF, and MITRE ATLAS cross-references alongside published mitigations.

Peaky8linders/eu-ai-act-scanner

Command

Scan a codebase, then propose concrete remediation (code edits, new files, tests) for the top compliance gaps. Does NOT auto-apply — always shows the plan first.

Peaky8linders/eu-ai-act-scanner

Command

Scan a codebase for EU AI Act compliance evidence and gaps. Produces a dimension-scored report with per-file findings, architecture graph, and prioritized recommendations.

Peaky8linders/eu-ai-act-scanner

Command

View or change the scanner's settings — mode (deterministic vs assisted) and autoapply. Assisted mode lets the plugin use your own Claude Code for semantic scanning, grounded Q&A, and applying fixes.