New framework: TAUSIK

TAUSIK, a verification layer for AI coding agents from maintainer Kibertum, released version v1.11.4 on Oct 12, 2026, gating task start and completion on specifications and evidence via MCP tools, skills, and host-dependent hooks. The framework, which declares conformance to SENAR Core and supports Claude Code, Codex, Qwen Code, Cursor, Kilo, and OpenCode, has 18 GitHub stars, 1 contributor, and 1 open issue, and its maintainer's reported token comparison found no token savings. TAUSIK's ed25519-signed receipts record checked code state, but the signing key is accessible in the working tree, so receipts provide integrity evidence rather than independent attestation against the agent.

TAUSIK experimental Verification layer for AI coding agents that gates task start and completion on specifications and evidence, with project memory and signed receipts. Reviewed 2 weeks ago · Sep 30, 2026 Website https://tausik.tech/ GitHub · Kibertum/tausik-core https://github.com/Kibertum/tausik-core Compare with other frameworks → https://sddobservatory.com/compare/?f=tausik,grill-me-skills,spec-kit - Stars - 18 - Contributors - 1 - Open issues - 1 - Age - 6 months - Last push - yesterday - Latest release - v1.11.4 Oct 12, 2026 View weekly commit data | Week starting | Commits | |---|---| | Oct 11, 2026 | 3 | | Oct 4, 2026 | 0 | | Sep 27, 2026 | 0 | | Sep 20, 2026 | 0 | | Sep 13, 2026 | 0 | | Sep 6, 2026 | 0 | | Aug 30, 2026 | 0 | | Aug 23, 2026 | 0 | | Aug 16, 2026 | 0 | | Aug 9, 2026 | 0 | | Aug 2, 2026 | 0 | | Jul 26, 2026 | 0 | | Jul 19, 2026 | 0 | | Jul 12, 2026 | 0 | | Jul 5, 2026 | 0 | | Jun 28, 2026 | 0 | | Jun 21, 2026 | 0 | | Jun 14, 2026 | 0 | | Jun 7, 2026 | 0 | | May 31, 2026 | 0 | | May 24, 2026 | 0 | | May 17, 2026 | 0 | | May 10, 2026 | 0 | | May 3, 2026 | 0 | | Apr 26, 2026 | 0 | | Apr 19, 2026 | 0 | | Apr 12, 2026 | 0 | | Apr 5, 2026 | 0 | | Mar 29, 2026 | 0 | | Mar 22, 2026 | 0 | | Mar 15, 2026 | 0 | | Mar 8, 2026 | 0 | | Mar 1, 2026 | 0 | | Feb 22, 2026 | 0 | | Feb 15, 2026 | 0 | | Feb 8, 2026 | 0 | | Feb 1, 2026 | 0 | | Jan 25, 2026 | 0 | | Jan 18, 2026 | 0 | | Jan 11, 2026 | 0 | | Jan 4, 2026 | 0 | | Dec 28, 2025 | 0 | | Dec 21, 2025 | 0 | | Dec 14, 2025 | 0 | | Dec 7, 2025 | 0 | | Nov 30, 2025 | 0 | | Nov 23, 2025 | 0 | | Nov 16, 2025 | 0 | | Nov 9, 2025 | 0 | | Nov 2, 2025 | 0 | | Oct 26, 2025 | 0 | | Oct 19, 2025 | 0 | Metrics updated Oct 13, 2026 · collected automatically from the GitHub API Core approach Runs over an existing agent through MCP tools, skills, and host-dependent hooks. QG-0 requires a goal and acceptance criteria before task start; QG-2 checks verification evidence before task completion. Scoped verification runs can issue ed25519-signed receipts recording the checked code state, while a local database preserves decisions and dead ends across sessions. Workflow 1. Install as a git submodule and run the Python bootstrap for the chosen host 2. /start — open a session and load project state and knowledge 3. /plan — capture requirements and create tasks with goals and acceptance criteria 4. /task <slug — pass QG-0 and implement within the task scope 5. tausik verify --task <slug — run scoped checks and issue a receipt when signing is configured 6. /ship — review, test, verify acceptance criteria, pass QG-2, and commit 7. /end — capture knowledge and prepare the session handoff Supported tools - Claude Code - Codex - Qwen Code - Cursor - Kilo - OpenCode Strengths - Task gates connect a written definition of done to recorded verification results - Signed receipts can be exported and checked offline with tausik receipt verify - Persistent project knowledge records decisions, patterns, and failed approaches - Integrates with several existing agents rather than requiring a replacement agent loop Limitations - Hooks are strongest in Claude Code, Qwen Code, and trusted Codex projects; other hosts primarily enforce task start and completion - The signing key is accessible in the working tree: receipts provide integrity evidence, not independent attestation against the agent - Verification coverage depends on declared scope and configured gates; recorded exceptions and unsigned completion paths exist - No general token savings or independent production outcomes were established; the maintainer's reported token comparison found no saving Notes TAUSIK Task Agent Unified Supervision, Inspection & Knowledge implements a task-specification and verification workflow over existing coding agents. It declares conformance to SENAR https://sddobservatory.com/frameworks/senar/ Core. The reviewed repository documents bootstrap installation, host integrations, task gates, receipts, and self-use in TAUSIK’s own development. The submission’s claim that every task needs a passing, signed receipt is broader than the documented behavior. The receipt guide retains a fresh-run completion path without an explicit signed handle, and the task reference documents a recorded acknowledgment when no test gate applies. Receipt scope divergence is recorded and does not always block completion. These distinctions matter when interpreting a green result. The experimental rating reflects limited independently verifiable adoption and the evolving verification contract. This review checked public documentation and the verify-first gate source; it did not run the software or independently validate the project’s self-reported effectiveness.