prime-radiant-inc

97 mods across 18 repositories, 1.4k stars between them.

prime-radiant-inc/parallel-adversarial-review

Skill Claude CodeCodex

Use when reviewing a diff, commit, branch, or implementation against a spec — dispatches two same-model reviewer subagents in parallel under a competitive scoring frame, then aggregates findings. Triggers on "review this", "PAR review", "adversarial review", or any evaluative gate (scope review, spec compliance, code…

17 2mo ago A 76 tokens

scenarios

74

prime-radiant-inc/scenarios

Settings file Claude Code

Agent settings configuring enableAllProjectMcpServers.

10 2mo ago A tokens not measured copy · 100% Apache-2.0

scenario-assistant

75

prime-radiant-inc/scenarios

MCP server Claude CodeCodexCursor +2

MCP server "scenario-assistant" as configured in prime-radiant-inc/scenarios. Runs locally from the ../../tools/mcp_server.py Python package.

10 2mo ago A tokens not measured original Apache-2.0

ledger-memory

77

prime-radiant-inc/ledger-memory

Plugin Claude Code

Ledger-backed persistent memory for coding agents: append-only facts with retraction vaccines, scars, and a generated MEMORY.md projection.

10 12d ago A tokens not measured original MIT

SessionStart

79

prime-radiant-inc/ledger-memory

Hook

Runs when a session starts on startup, resume, clear, compact and fork, executing session-start.sh. From prime-radiant-inc/ledger-memory.

10 12d ago A tokens not measured original MIT

PreToolUse

80

prime-radiant-inc/ledger-memory

Hook

Runs before the agent uses a tool for Bash tool calls, executing pre-tool-guard.py. From prime-radiant-inc/ledger-memory.

10 12d ago A tokens not measured original MIT

ledger-memory

81

prime-radiant-inc/ledger-memory

Skill Claude CodeCodex

Use when saving, correcting, or curating persistent memory — recording facts for future sessions, retracting wrong memories, end-of-session housekeeping, or deciding what deserves remembering.

10 12d ago A 37 tokens original MIT

linear-use

82

prime-radiant-inc/agent-plugin-linear-use

Plugin Claude Code

Keep AI-driven work tracked in Linear: a skill that finds or creates a ticket and moves it through your workflow states, plus a hook that nudges the agent to do it. An example of how Prime Radiant works.

6 26d ago A tokens not measured original MIT

prime-radiant-inc/agent-plugin-linear-use

Skill Claude CodeCodex

TRIGGER when: user asks to fix, build, add, implement, refactor, update, or change code; when resuming a feature branch; when finishing implementation or creating a PR. Finds or creates a Linear ticket, moves to In Progress at start, In Review at finish. Required — work without a ticket is untracked.

6 26d ago A 73 tokens original MIT

pr-security-review

96

prime-radiant-inc/github-triage

Agent

Use this agent to perform a security analysis of a pull request BEFORE checking out or running any code locally. Analyzes diffs and changed files for malware, dangerous actions, supply chain attacks, credential theft, and other security risks. Returns a verdict of SAFE, REVIEW NEEDED, or BLOCK. Must be run before any…

4 20d ago C 75 tokens