HARNESS-SPEC Reference

Location: ~/.claude/HARNESS-SPEC.md
Current Version: 3.1
Format: Markdown with YAML/JSON/ASCII code blocks


What Is HARNESS-SPEC?

HARNESS-SPEC is the single canonical configuration document that describes every component of the godotz.ai harness on a given machine. It is a point-in-time snapshot of the full fleet node configuration: packages, plugins, hooks, agents, skills, model routing, optimization layers, memory backends, and tooling.

The document is not generated — it is authored and maintained by hand (or by the harness-legacy-scan workflow) and lives at ~/.claude/HARNESS-SPEC.md. When a session agent loads it, it has authoritative ground truth about what is installed, what version, and why each design decision was made.

It serves three purposes:

  1. Fleet baseline — establishes the exact state of a node so drift from this baseline can be detected
  2. Onboarding reference — lets a new session agent (or engineer) reconstruct full context without interrogating the filesystem
  3. Decision log — records design rationale in Section 24 so future changes have provenance

Section Overview

HARNESS-SPEC v3.1 contains 27 sections:

§TitleWhat it covers
1Package RegistryCore packages: godotz.ai, OMC, Claude Code, Caveman, gstack, Knowledge Gardener, GLM Plan Usage, context7, Graphify — with versions and install commands
2Configuration FilesAll settings files: ~/.claude/settings.json (global), settings.local.json (local permissions), .omc-config.json (OMC runtime), project-level settings.json, godotz.ai agent/config.yml (hardcore preset), and 6 auxiliary config files
3Plugins9 installed Claude Code plugins with IDs, versions, scope, and marketplace source
4HooksAll hook points: 5 global hooks, 2 project hooks, 24 OMC hook scripts across 11 event types, 3 Knowledge Gardener hooks, and the Caveman hook state
5CLAUDE.mdGlobal context file structure — operating principles, delegation rules, model routing, Tier-0 skills, keyword triggers, kill switches
6Agents32 total agents: 1 user-defined (evaluator), 20 OMC built-in, 3 Caveman (cavecrew-builder/investigator/reviewer), 8 godotz.ai Swarm agents across two workloads
7RulesTDD rule at ~/.claude/rules/tdd.md — RED-GREEN-REFACTOR, scope, exceptions
8Workflows2 workflows: harness-legacy-scan.md (7-agent read-only audit) and harness-diet.md (low-risk cleanup)
912-Layer Optimization StackFull architecture diagram + per-layer detail: preset toggle (L1), confidence-gate cascade (L2), pheromone routing (L3), semantic cache (L4), plan cache (L5), context engineering (L6), EMA tracker (L7), budget control (L8), regression gate (L9), context hydration (L10), Graphify knowledge graph (L11), orchestrate keyword (L12)
10Model ArchitectureConversation models (Antigravity: opus/sonnet/gemini), worker models (GLM: glm-5.1/4.7/4.5-air), concurrency limits per model, vision fallback, swarm constraints, local GPU model
11Swarm SystemTwo completed swarm workloads with DAG topology, phase descriptions, and execution results
12Skills128 total skills: 27 user-defined, 41 OMC built-in (including 37 core + 4 additional), 60 gstack sub-skills with category breakdown
13MCP Servers7 active MCP servers with tool counts: chrome (15), context7 (2), OMC bridge (49), web-reader (1), web-search-prime (1), zai-mcp-server (8), zread (3)
14HUDStatus line configuration — command path, file size, helper library location
15Memory SystemAll active memory backends: Mnemopi (SQLite + WAL), auto-resume, session mental model (8K tokens), Knowledge Vault (~/vault, 9 folders), session capture, auto-recap
16Tool Scripts11 godotz.ai optimization scripts in ~/.local/bin/ with language, path, and purpose
17Data Files17 data files in ~/.omp/ — JSON/YAML/SQLite — with types and contents
18Kernel Tuning5 sysctl parameters tuned at /etc/sysctl.d/99-claude-optimization.conf
19Daemons & SessionsClaude Code daemon paths, session logs, history, background jobs, task state
20Active ProjectCurrent project (omp-playground): tech stack, source tree, and generated artifacts
21Directory TreeFull annotated directory listing of ~/.claude/, ~/.omp/, ~/.local/bin/, and project root
22Execution FlowEnd-to-end hook sequence diagram from session start through tool use, subagent lifecycle, compaction, and session end
23Benchmark Results10 graded performance metrics (S/A grades) from the 12-layer optimization stack
24Design Decisions8 architectural decisions with rationale — model split, compaction strategy, pheromone evaporation rate, etc.
25Known Limitations8 documented limitations: Antigravity concurrency unknown, GPU excluded from subagents, pheromone DB test bias, regression placeholder tests, plan cache exact-match only, budget enforcement external only, cascade manual, config ceiling reached
26Roadmap7 future items with status and dependencies: Self-Evaluating Controller, Adaptive Router, Prompt Evolution, Cross-Session Intelligence, Cost-Quality Pareto, A2A Protocol, large codebase testing
27Statistics SummaryAggregate counts across all categories — packages, plugins, agents, skills, hooks, rules, workflows, MCP servers, optimization scripts

How to Read HARNESS-SPEC

Start with Section 27 (Statistics Summary) for a numeric inventory of what is present. This tells you the scale before diving into specifics.

Navigate by need:

  • Troubleshooting a hook firing unexpectedly → Section 4
  • Understanding why a model was chosen → Sections 10 and 24
  • Adding a new plugin → Sections 3 and 2 (check marketplace sources)
  • Auditing optimization scripts → Sections 9 and 16
  • Inspecting memory behavior → Section 15
  • Understanding execution order → Section 22 (execution flow diagram)

Code blocks are authoritative. The YAML in Section 2.5 (~/.omp/agent/config.yml) is the actual file content, not a summary. JSON blocks in Section 2 reproduce real settings.

Design decisions are documented in Section 24. Before changing a setting that seems arbitrary (e.g., pheromone evaporation rate = 0.05, compaction threshold = 180K tokens), check Section 24 first — the reasoning is there.


Relationship to Fleet Baseline Snapshots

HARNESS-SPEC is the fleet baseline snapshot format for godotz.ai nodes. Each time the configuration changes materially (new plugin, model update, optimization layer added), the spec is re-authored and the version number increments (v1.0v3.0v3.1).

Baseline drift detection works by diffing the current node state against the spec:

  • Plugin versions in Section 3 vs. installed_plugins.json
  • Model versions in Section 2.5 vs. ~/.omp/agent/config.yml
  • Script presence in Section 16 vs. ~/.local/bin/ contents

The harness-legacy-scan workflow (Section 8) runs a 7-agent read-only audit that compares live state against the spec and surfaces drift, dead code, and overlap. The output informs harness-diet.md cleanup passes.

Multi-node fleets use per-node copies of HARNESS-SPEC. The document begins with a hardware/OS header (see v3.0: Linux x64, i9-12900K, RTX 3080, 30Gi RAM) that identifies the specific node. Diffing two HARNESS-SPEC documents reveals exactly what differs between fleet nodes.


Updating the Spec

HARNESS-SPEC is updated manually after significant configuration changes. The convention is:

  1. Run harness-legacy-scan to get a current-state audit
  2. Update the affected sections with exact values (versions, paths, counts)
  3. Add a row to Section 24 if the change reflects a design decision
  4. Increment the patch version in the document header
  5. Update the Statistics Summary (Section 27) aggregate counts

The spec is not auto-generated because agent-authored prose in the design decisions, known limitations, and roadmap sections requires human judgment to keep accurate.