TechTide Harness Kit
TechTide Harness Kit uses JSON Schema to declare skill permissions, risk tiers, network access, and approval requirements. Automated checks validate declarations and run prompt-injection fixtures.
Project details
- Classification
- Open-source project
- Repository
- TechTideOhio/techtide-harness-kit
- Language
- Python
- License
- Apache-2.0
- Status
- Maintained
- Tests
- 3 test notes
- Last verified
- 2026-07-27
What it is
I use the Harness Kit to make skill rules checkable in code. Each skill declares its risk tier, allowed tools, and network access. Continuous integration checks those declarations and runs prompt-injection fixtures. You can inspect the schemas, fixtures, and workflow files in the repository.
Architecture
- JSON Schema contracts define risk tiers, tool permission sets, and egress allowances per skill.
- Deny-by-default egress: a skill reaches nothing it has not declared.
- Approval gates attach to tiers rather than to individual call sites, so escalation is uniform.
- Prompt-injection fixtures live beside the contracts and run as tests.
- Provider scope regression checks guard against a skill silently widening its permissions across releases.
Tests and gates
- Nine GitHub Actions workflows: ci, codeql, docs-quality, install-paths-smoke, packed-artifact-smoke, provider-scope-regression, apply-ruleset, release, and OpenSSF scorecard.
- CI validation gates run across those workflows; the workflow files are the source of truth for what is checked.
- CONTROL-MAPPING.md, DATA-HANDLING.md, TRUST.md, EVALS.md, and PROMPT-INJECTION.md document what each gate is asserting.
Limits
- The kit checks declarations and test fixtures. Passing them cannot establish that a model will resist every prompt-injection attempt.
- Contracts are only as tight as the author makes them; a permissive tier is still permissive.
- Coverage is aimed at Claude Code, Codex, Cursor, and Kiro style skill packages, not at every agent runtime.
Source files and examples
- README →github.com/TechTideOhio/techtide-harness-kit#readme
- Trust contracts →github.com/TechTideOhio/techtide-harness-kit/blob/master/TRUST.md
- Prompt-injection fixtures →github.com/TechTideOhio/techtide-harness-kit/blob/master/PROMPT-INJECTION.md
- Control mapping →github.com/TechTideOhio/techtide-harness-kit/blob/master/CONTROL-MAPPING.md
- Evals →github.com/TechTideOhio/techtide-harness-kit/blob/master/EVALS.md
Related methods
Acceptance tests for agent work →
Executable checks test the task and detect regressions.
Evaluation tests for releases →
A fixed evaluation suite checks release requirements.
MCP tool permissions →
The server checks which tools a caller may use.
Recording agent runs →
A shared trace ID connects the records of a run.
Spending limits for agent runs →
Budget checks run before provider requests.
Pausing for human approval →
The run waits for approval before the action executes.
Related projects
ClawKeeper →
ClawKeeper checks proposed Claude agent actions against explicit rules before a model call. Autonomous spend defaults to zero, and the database enforces an append-only audit log.
CipherClaw →
CipherClaw analyzes recorded agent activity without model calls. It builds causal graphs, scores possible causes, and flags failure patterns.
Swarm 357 →
357 Claude agent roles across six business layers, with portable memory, enforced cost caps, a bash policy gate, and durable checkpoints.
FintheFinder →
FintheFinder pauses research runs for human approval and audits citations deterministically. Its repository includes contracts and test files.
I document the project here. TechTide AI publishes current service scope, prices, and terms.
Systems Decision Audit at TechTide AI→© 2026 Alex Cinovoj · TechTide AI · Columbus, OH