mivia-agentkit
AGENTS.md2 starsChanged 4 months agoMITView on GitHub
Root AGENTS.md is canonical. Read it first, then .ai/INDEX.md. .codex/hooks.json delegates through scripts/run_agent_hook_guard.sh, which applies the repo guard before any future mivia-agent handler. Intended Codex event mapping: Hook payloads are JSON on stdin. Handlers must read common fields such as session_id, cwd, hook_event_name, permission_mode, and event-specific fields such as prompt, tool_name, tool_input, or last_assistant_message. Handlers must return JSON decisions or exit 2 with a scrubbed reason when blocking. The committed fallback guard rejects verification-bypass attempts and gives the model corrective…
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- adversarial-test-reviewSkill
- agent-dag-plannerSkill
- agent-plan-implementerSkill
- airtight-feature-deliverySkill
- deep-bug-auditSkill
- mivia-agent-workflowsSkill
- test-coverage-auditSkill
- adversarial-test-reviewSkill
- agent-dag-plannerSkill
- agent-plan-implementerSkill
- airtight-feature-deliverySkill
- deep-bug-auditSkill
- mivia-agent-workflowsSkill
- test-coverage-auditSkill
The file
Files
Codex Adapter
Root AGENTS.md is canonical. Read it first, then .ai/INDEX.md.
.codex/hooks.json delegates through scripts/run_agent_hook_guard.sh, which applies the repo guard before any future mivia-agent handler. Intended Codex event mapping:
UserPromptSubmit->mivia-agent hook codex user-prompt-submitPreToolUse->mivia-agent hook codex pre-tool-usePermissionRequest->mivia-agent hook codex permission-requestStop->mivia-agent hook codex stop
Hook payloads are JSON on stdin. Handlers must read common fields such as session_id, cwd, hook_event_name, permission_mode, and event-specific fields such as prompt, tool_name, tool_input, or last_assistant_message. Handlers must return JSON decisions or exit 2 with a scrubbed reason when blocking. The committed fallback guard rejects verification-bypass attempts and gives the model corrective repair instructions.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.