ruvnet
e332689b8c
fix(release): harden hooks, statusline, security, and plugin MCP integration
2026-07-16 23:06:29 -04:00
ruv
e4ecb88ae3
darwin-plugins iter 3 — ruflo-intelligence: align plugin.json tool-count breakdown with README inventory
2026-06-26 20:28:10 -04:00
ruv
a73ff2980d
darwin-plugins iter 1 — ruflo-intelligence: correct Tier 1 to deterministic codemod (ADR-143)
2026-06-26 20:02:14 -04:00
Reuven and RuFlo
78e5658dfd
feat(ruflo-intelligence): v0.3.0 — surface completeness, 4-step pipeline, IPFS transfer, namespace coordination
...
Implements ADR-0001 for ruflo-intelligence. Plugin previously documented
~14 of 29 intelligence-related MCP tools and never operationalized the
4-step pipeline (RETRIEVE → JUDGE → DISTILL → CONSOLIDATE) that CLAUDE.md
treats as the V3 framing. IPFS-based cross-project pattern transfer
(hooks_transfer) was completely invisible despite being a real
differentiator.
Verified surface (29 tools across 5 families):
- 6 neural_* (incl. neural_compress, previously undocumented)
- 10 hooks_intelligence_*-family (incl. _attention, _learn, _stats,
-reset — all previously undocumented)
- 6 routing/meta hooks (hooks_route, hooks_explain, hooks_pretrain,
hooks_build-agents, hooks_metrics, hooks_transfer — last 5
previously undocumented)
- 3 hooks_model-* (Tier 1/2/3 routing)
- 4 ruvllm_sona_* + ruvllm_microlora_* (MicroLoRA previously undocumented)
Changes:
- bump 0.1.0 → 0.3.0; new keywords (microlora, ewc, attention, moe,
pattern-transfer, model-routing, mcp)
- ADR-0001 (Proposed): documents drift, decisions, smoke contract,
namespace coordination with ruflo-agentdb
- README: full rewrite with tool inventory + 4-step pipeline (each phase
mapped to specific tool calls) + cross-project IPFS transfer + hook
integration table + namespace coordination (defers to ruflo-agentdb
ADR-0001) + EWC++ explanation (no longer phantom feature) + MoE mode
enumeration + Compatibility section
- intelligence-specialist agent: tool routing matrix (29 entries),
pipeline responsibility table, namespace contract, MoE mode selection,
EWC++ in practice, cross-project transfer flow
- /intelligence command: real dashboard (stats + metrics + model-stats
+ neural-status + hooks_explain on --why)
- /neural command: adds neural_compress dispatch
- intelligence-route skill: adds hooks_explain rationale step
- neural-train skill: adds MicroLoRA section, EWC++ via consolidate flag,
hooks_pretrain + hooks_build-agents bootstrap, hooks_intelligence-reset
for testing
- NEW intelligence-transfer skill: walks the IPFS workflow end-to-end
(store / load / from-project), Pinata prerequisite documented
- scripts/smoke.sh: 16 structural checks (3 doc invariants + 13 contract)
Verification:
bash plugins/ruflo-intelligence/scripts/smoke.sh
→ 16 passed, 0 failed
Coordinates with prior ADRs:
- ruflo-agentdb ADR-0001 §"Namespace convention" — pattern (singular)
vs patterns (plural) gotcha referenced inline
- ruflo-ruvector ADR-0001 — trajectory hooks land in ruvector substrate
- ruflo-browser ADR-0001 — consumes trajectory hooks for replay
Co-Authored-By: RuFlo <ruv@ruv.net >
2026-05-04 19:39:44 -04:00
Reuven
2e5c90c902
feat(plugins): ADR-098 Part 4 — standardize neural-learning hook
...
Closes the 16% gap (7 of 43 plugin agents) flagged by the ADR-098
audit: agents that completed tasks without feeding the SONA learning
loop, costing the system long-term improvement signal.
Each affected agent gets the canonical 5-line tail:
### Neural Learning
After completing tasks, feed the <role-specific-context>:
```bash
npx @claude-flow/cli@latest hooks post-task --task-id "TASK_ID" --success true --train-neural true
```
The "<role-specific-context>" is per-agent so the tail reads native
rather than copy-pasted:
ruflo-daa/daa-specialist adaptive-agent learning loop
ruflo-goals/goal-planner planner trajectory store
ruflo-intelligence/intelligence-spec pattern-discovery learning loop
(next RETRIEVE benefits from this run)
ruflo-iot-cognitum/telemetry-analyz telemetry baseline learning
(Z-score thresholds adapt)
ruflo-ruvllm/llm-specialist router outcome learning
(provider/model picks compound)
ruflo-sparc/sparc-orchestrator phase-quality learning loop
(quality gates self-tune)
ruflo-swarm/coordinator coordination outcome learning
(topology + role choices compound)
Re-audit confirms 0 of 43 plugin agents missing the hook (was 7 of 43).
ADR-098 acceptance-criteria item closed: "All 43 plugin agents include
a `hooks post-task --train-neural true` invocation."
Parts 1 (capability sync), 2 (token diet), 3 (model rightsizing), and
5 (worker dispatch) remain as separate iterations.
2026-05-03 21:56:52 -04:00
Reuven and claude-flow
f25bcf2073
feat: add 10 new ruflo plugins, optimize all 32, add READMEs and user guide
...
New plugins: ruflo-adr (ADR lifecycle), ruflo-ddd (domain-driven design),
ruflo-sparc (SPARC methodology), ruflo-neural-trader (trading strategies),
ruflo-ruvector (vector embeddings), ruflo-knowledge-graph (entity graphs),
ruflo-market-data (OHLCV ingestion), ruflo-migrations (schema management),
ruflo-observability (logging/tracing), ruflo-cost-tracker (token budgets).
Optimizations across all 32 plugins:
- All pass `claude plugin validate` (removed invalid manifest arrays)
- 51/51 skills have argument-hint frontmatter
- Model routing: 4 haiku, 24 sonnet, 2 opus (cost-optimized)
- Neural learning hooks on 25/30 agents
- Cross-references between 6 related plugin pairs
- Pathfinder graph traversal algo for researcher agent
- READMEs for all 32 plugins + plugins/README.md catalog
- discover-plugins skill updated with full 32-plugin catalog
Co-Authored-By: claude-flow <ruv@ruv.net >
2026-04-29 23:46:54 -04:00
Reuven and claude-flow
81418649c6
feat: add 19 Claude Code native plugins with 64 skills, 25 commands, 21 agents
...
Complete plugin marketplace for Ruflo with validated Claude Code plugin format:
- ruflo-core: MCP server, status, doctor, plugin discovery
- ruflo-swarm: swarm coordination, Monitor, worktree isolation
- ruflo-autopilot: autonomous /loop completion with learning
- ruflo-intelligence: SONA neural patterns, trajectory learning, routing
- ruflo-agentdb: AgentDB controllers, HNSW vector search, RuVector
- ruflo-aidefence: AI safety scanning, PII detection, prompt defense
- ruflo-browser: Playwright browser automation, testing, scraping
- ruflo-jujutsu: git diff analysis, risk scoring, reviewer recs
- ruflo-wasm: sandboxed WASM agents and gallery sharing
- ruflo-workflows: workflow templates, orchestration, lifecycle
- ruflo-daa: Dynamic Agentic Architecture, cognitive patterns
- ruflo-ruvllm: local LLM inference, MicroLoRA, SONA, chat format
- ruflo-rvf: RVF portable memory, session persistence, transfer
- ruflo-loop-workers: background /loop workers, CronCreate
- ruflo-security-audit: CVE scanning, dependency checks
- ruflo-rag-memory: simple store/search/recall interface
- ruflo-testgen: test gap detection, TDD workflow
- ruflo-docs: doc generation, drift detection
- ruflo-plugin-creator: scaffold, validate, publish new plugins
All 19 pass `claude plugin validate`. Skills auto-discovered from
directory structure (not declared in plugin.json). Each skill wires
to ruflo MCP tools via allowed-tools frontmatter.
Includes: marketplace.json, GitHub Pages storefront, CI validation
workflow, minimalist README with USERGUIDE split.
Co-Authored-By: claude-flow <ruv@ruv.net >
2026-04-27 23:07:33 -04:00
ruvnet