Code-Munkiz

Code-Munkiz/ham

Cursor rule Cursor

Subagent charter: Context Engine Auditor. Applies when reviewing memoryheist.py.

Code-Munkiz/ham

Cursor rule Cursor

Subagent charter: Execution Safety Auditor. Applies when reviewing droidexecutor.py.

Code-Munkiz/ham

Cursor rule Cursor

Subagent charter: Reviewer Loop Auditor. Applies when reviewing hermesfeedback.py.

Code-Munkiz/ham

Cursor rule Cursor

Keep VISION.md aligned with actual repo state after milestone work.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

Minimal starter runbook for Cloud agents to install, run, and test Ham quickly. Covers backend/frontend startup, chat gateway modes, Cursor key setup, browser runtime checks, and how to keep this skill current as new runbook knowledge is found.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

Harden memoryheist.py against token blowouts, unbounded growth, cross-platform path bugs, stale Claude references, and continuation/parser marker drift. Use when modifying memoryheist.py, fixing compaction logic, capping diffs, or adding safety limits to the Context Engine.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

How Ham previews and launches allowlisted Factory droid exec workflows from chat (readonly audit vs low-risk edit), runner assumptions, and hard security limits. Instructional only — policy lives in code.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

Guides conversational navigation of the Ham dashboard: settings sections, projects, Droids/registry, runs and activity, and how to scaffold sub-agent workflows or new assets using existing APIs and configs. Use when the user wants natural-language help finding settings, understanding Hermes vs Droid roles, creating…

Code-Munkiz/ham

Skill Claude CodeCodexCursor

Review executor prompts for red flags, alignment issues, blockers, scope drift, and evidence gaps before any non-trivial execution.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

Validate the Hermes supervisory critic review loop: verify Hermes receives correct context, invokes HermesReviewer.evaluate(), and preserves learning signals for later persistence. Use when modifying hermesfeedback.py, the supervisory review path, or the review pipeline.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

Structured diagnosis loop: reproduce, minimize, hypothesize, instrument, fix, and regression-test.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

Grilling session for plan alignment against domain language and ADRs, with inline doc updates when decisions are finalized.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

Summarize the current thread into a compact handoff artifact for a fresh agent session.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

PARKED/MANUAL ONLY: Identify architecture deepening opportunities and refactor candidates.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

Repo-local setup for Matt Pocock engineering skills in HAM. Configures issue tracker, triage labels, and domain doc locations without touching runtime or deploy settings.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

Red-green-refactor loop using vertical slices and behavior-focused tests through public interfaces.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

Convert accepted plans/specs into independent vertical-slice GitHub issues with explicit dependencies.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

Turn current conversation context into a PRD-style implementation issue with explicit module and testing decisions.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

PARKED/MANUAL ONLY: Triage issue workflow through category/state labels when explicitly requested.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

Explain a subsystem at a higher abstraction level and map related modules/callers before editing.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

Audit token budgets across the Ham swarm to prevent context window overflows. Use when checking prompt sizes, reviewing MAX constants, or diagnosing truncation issues in agent outputs.

Code-Munkiz/ham

Skill Claude CodeCodexCursor

Test that memoryheist.py correctly scans the repo, discovers configs and instructions, captures git state, and compacts sessions without data loss. Use when adding tests for Context Engine changes or verifying cross-platform behavior.

Code-Munkiz/ham

Instructions file CodexOpenCode

AGENTS.md instructions for Code-Munkiz/ham, covering ham — agent context index, read order (recommended), ham bet: memory, hermes, and cli-native muscle, architecture and pillar modules.

Code-Munkiz/ham

Agent

Ops note: auth and env changes are not performed from this document. This captures a product/engineering decision and rollout reminders only.