Hook Claude Code
Runs before the agent uses a tool for WebFetch, WebSearch, Write, Edit and Bash tool calls, running an inline shell check (2 commands). From dollspace-gay/chainlink.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, running an inline shell check. From dollspace-gay/chainlink.
Hook Claude Code
Runs after a tool call finishes for Write and Edit tool calls, running an inline shell check. From dollspace-gay/chainlink.
Hook Claude Code
Runs when a session starts on startup and resume, running an inline shell check. From dollspace-gay/chainlink.
Settings file Claude Code
Agent settings declaring 4 hook events (PreToolUse, UserPromptSubmit, PostToolUse, SessionStart).
MCP server Claude CodeCodexCursor +2
MCP server "chainlink-safe-fetch" as configured in dollspace-gay/chainlink. Runs .claude/mcp/safe-fetch-server.py with python.
Instructions file
Instructions for dollspace-gay/chainlink, covering chainlink issue tracker, commands, issues, organization and sessions.
Hook Claude Code
Runs before the agent uses a tool for WebFetch and WebSearch tool calls, executing pre-web-check.py via python. From dollspace-gay/AethelOS.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing prompt-guard.py via python. From dollspace-gay/AethelOS.
Hook Claude Code
Runs after a tool call finishes for Write and Edit tool calls, executing post-edit-check.py via python. From dollspace-gay/AethelOS.
Hook Claude Code
Runs when a session starts on startup and resume, executing session-start.py via python. From dollspace-gay/AethelOS.
Settings file Claude Code
Agent settings declaring 4 hook events (PreToolUse, UserPromptSubmit, PostToolUse, SessionStart).
MCP server Claude CodeCodexCursor +2
MCP server "chainlink-safe-fetch" as configured in dollspace-gay/AethelOS. Runs .claude/mcp/safe-fetch-server.py with python.
Instructions file
Instructions for dollspace-gay/AethelOS, covering claude.md - ai assistant guide to aethelos development, build commands, 1. build the kernel and iso, 2. run in qemu and prerequisites.
Skill Claude CodeCodex
Use when bootstrapping a "vibe fork" — sequential translation of a known-working upstream codebase to a new substrate (e.g. C kernel → Rust kernel, PyTorch C++ → Rust ML framework, COBOL → Java). Installs the 4-agent ACToR loop (doc-author / builder / critic / fixer), the read-gate hook that enforces "read upstream +…
Agent
Multi-file/cross-crate authorized agent for shipping missing infrastructure that exceeds acto-fixer's single-file scope. Use when the divergence is "an entire abstraction is missing" — a newtype + every consumer, an entire op family + dispatch, a typestate threaded through the call graph — rather than "a constant has…
Agent
ACToR-style discriminator for upstream ← target translation audits. Hunts for semantic divergence between the target implementation and the upstream source it claims to translate. ALWAYS writes a FAILING test that pins down the divergence — NEVER writes a fix. Dispatch when the prior implementation iter declares…
Agent
Authors design docs under .design/ / .md that ADAPT to existing target code. Each REQ status table is grounded in quoted-code evidence from the current /src/ . implementation. REQs are classified BINARY — SHIPPED (end-to-end functional with non-test production consumer + tests + verification passes) or NOT-STARTED…
Agent
Applies the MINIMAL fix for exactly ONE pinned divergence found by acto-critic. The failing test pins the divergence; the fix makes that test pass. Never bundles multiple fixes. Never refactors adjacent code. Never touches files outside the one the divergence is in. After the fix, runs the full gauntlet (test + clippy…