π The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
Changelog: ruflo-workflows
Newest first. One ## <version> β <date> heading per version, then feat:, fix:, breaking: and chore: bullets (ADR-478). Built from git history; older versions: git log -- plugins/ruflo-workflows.
0.7.1 β 2026-10-29
- chore: operational skills are user-invoked only (
disable-model-invocation: true) and long skill/command descriptions are cut to one sentence, so they cost less prompt on every turn (ADR-507, #4588). Every skill is still available as/<skill>.
0.7.0 β 2026-10-24
- feat: managed workflow capability discovery, bounded local mod policy and console policy metadata
- fix: ship the managed workflow integration through a versioned plugin update
0.6.7 β 2026-10-12
- fix: the shared text screen now catches
.envand e-mailed credentials, no longer flags a model's token talk (--max-tokens,/oauth/token, "token usage"), and no longer flags values that only name where a secret lives (./service-account.json,--set-secrets=NAME=NAME:latest); every rule stays linear (#4094, thanks @proffesor-for-testing)
0.6.6 β 2026-10-11
- fix: skills gaia-submission and gaia-debugging named MCP tools that do not exist (
hooks_post_task,hooks_pre_task,agentdb_pattern_search,agentdb_pattern_store); the real names use a hyphen, so the tools were never pre-approved - fix:
gaia-bench runhas no--dry-runor--task-id(unknown flags are ignored, so the documented cost-estimate and 1-question check started a real, billed run); docs now say so and give a cost estimate path that does not spend,--votingcorrected to--voting-attempts - chore: smoke-gaia.sh expected version 0.4.0 and component arrays in plugin.json (both obsolete, 2 checks failing since 0.6.x); it now checks semver >= 0.4.0 and that no component arrays are declared
- fix: workflow-run asks for the user's opt-in before starting a native workflow and states how many agents it will start
0.6.5 β 2026-10-09
- chore: drop the unused
componentskey from plugin.json (claude.ai plugin validator warns on it; nothing read it)
0.6.4 β 2026-10-07
- feat: workflow-create documents the two ADR steps (requires ADR, records ADR) that use the project's own ADRs through ruflo-console's ADRs page (ADR-480)
0.6.3 β 2026-10-05
- fix: shared textsOf reports truncation and every guard fails closed on it
0.6.2 β 2026-10-04
- feat: vendor the flag option parser from one origin with the screen sync and drift check (review #2)
- fix: one iterative textsOf in the shared screen β depth, sibling, size caps, object keys and the invisible-character set fixed at the root (ADR-β¦
- fix: secret screen β a 20+ char value under a secret-named key is a secret even all-letter or UUID-shaped, unless a clear reference (ADR-445)
- fix: secret screen judges values, not names β fewer false positives, vendor keys, URL credentials, env assignments, 200 KB scan (ADR-445)
- chore: one source for the secret screen β sync-mod-screen.mjs regenerates the shared region of 37 screen.ts copies, --check in all-plugins-smoke (β¦
0.6.1 β 2026-10-04
- fix: live-check W5 β guards read key names and every field; trader gates the package's real order tools
0.6.0 β 2026-10-04
- feat: function-hook mod (guard, status file, local slash command)
0.5.1 β 2026-07-16
- fix: harden hooks, statusline, security, and plugin MCP integration
0.5.0 β 2026-07-03
- feat: pre-submission exploit audit + signed attestation (ADR-167)
- chore: darwin-plugins iter 1 β ruflo-workflows: add 'Use when' trigger to gaia-debugging skill (ADR-112)
0.4.0 β 2026-05-29
- fix: stale route cache + --explore false (3.10.8)
0.3.0 β 2026-05-27
- fix: #2156 iter 53a β narrow T2 extraction to fix iter 52b regression
- chore: bulk-update plugin contract ADR statuses (sweep)