Compare two JSON records describing agent setups and their scores. Receive an overall similarity score with component details to help assess reuse, compare template candidates, identify overlapping work, or check how much a setup has changed.
ADR-152 — weighted similarity between two harness fingerprints (genome + score JSON). Returns overall score in [0,1] plus per-component breakdown (cosine over 9 numerics, categorical agreement over 4 enums, jaccard over agent_topology). Unblocks ADR-151 §3.2 Recommender, §3.3 Drift Detection, §3.5 Plugin Compat. Pure-TS, no `@metaharness/*` dep — preserves ADR-150's four architectural constraints.
harness-similarity compares feature data and evaluation scores for two harnesses, which describe how agents are set up to run. It returns a similarity score from 0 to 1. The calculation combines nine numerical fields, four categorical fields, and shared elements of the agent setup, weighted at 60%, 25%, and 15%, respectively. You can inspect both the overall score and its component breakdown.
The comparison provides information for deciding whether to adapt an existing setup or create a new one. It also helps rank template candidates for a target repository and identify overlapping work in setups created by different teams. An alert when similarity falls below a specified threshold helps you check changes to a setup.
Inputs must be JSON containing harness features and evaluations, rather than arbitrary text. You can specify files or saved record keys. Use the ruflo CLI or its corresponding MCP tool. Malformed inputs return a degraded result with a reason and exit code 2. No additional packages or @metaharness/* imports are required.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.
The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 21, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Surfaces the production similarity function from scripts/_similarity.mjs as a callable skill. Use when an agent needs to:
overall = 0.60·cosine + 0.25·categorical + 0.15·jaccard
repo_type, archetype, template, recommendedMode)|A ∩ B| / |A ∪ B| over the agent_topology[] arrayThe 3-component design is load-bearing: numerical cosine alone is too coarse (the iter-35 spike showed LEGAL vs DEVOPS at cosine=0.97 despite being unrelated verticals). Categorical + jaccard pull the composite to the correct ordering.
| Pair | overall | cosine | categorical | jaccard |
|---|---|---|---|---|
LEGAL × LEGAL (self) | 1.0000 | 1.0000 | 1.0000 | 1.0000 |
LEGAL × SUPPORT | 0.8296 | 0.9987 | 0.7500 | 0.2857 |
LEGAL × DEVOPS | 0.5840 | 0.9734 | 0.0000 | 0.0000 |
Both invariants from ADR-152 §"Smallest demonstrable spike" hold:
similarity(X, X) === 1 exactlysimilarity(LEGAL, DEVOPS) < similarity(LEGAL, SUPPORT) (vertical affinity)@metaharness/* imports.package.json.{ degraded: true, reason } with exit code 2; never throws.# File inputs
npx ruflo metaharness similarity --a a.json --b b.json
# Memory inputs (records persisted by oia-audit.mjs)
npx ruflo metaharness similarity --a-key harness-X --b-key harness-Y
# Per-dimension breakdown (used by ADR-151 §3.2 Recommender)
npx ruflo metaharness similarity --a a.json --b b.json --per-dimension
# Alert when too-dissimilar (used by ADR-151 §3.3 Drift Detection)
npx ruflo metaharness similarity --a a.json --b b.json --alert-below 0.5
Production module: scripts/_similarity.mjs
CLI skill: scripts/similarity.mjs
MCP tool: mcp__plugin_ruflo-core_ruflo__metaharness_similarity (registered in v3/@claude-flow/cli/src/mcp-tools/metaharness-tools.ts)
Spike anchor: scripts/_spike-similarity.mjs (regression suite — invariants locked here)
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.
Create an Architecture Decision Record, a document for recording important design choices, with the next sequential number. It generates a Markdown template, registers the record in AgentDB, and links related decisions found through search.
Build a searchable index and relationship graph from ADRs, records of architectural decisions. Import two supported document formats, refresh existing metadata without duplicate relationships, and review summaries of statuses, missing references, and inconsistencies.
Rebuild the index of ADRs, records of architectural decisions, after files or relationship lines are deleted. It clears stored records and relationships, indexes the files still present, and checks that the final record count matches.
Review code changes against accepted Architecture Decision Records, documents that capture agreed design choices. Report violations, outdated references, compliant changes, and areas without ADR coverage, then suggest code fixes or a new decision record where appropriate.
Check saved architecture decision records (ADRs) for broken references, circular replacement relationships, and inconsistent statuses. Use the results to verify imported records or stop a CI check when selected integrity rules fail.