Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/furkantokkan/agent-foundryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/furkantokkan/agent-foundry/unity-test-verifier)<a href="https://agentmods.dev/agents/furkantokkan/agent-foundry/unity-test-verifier"><img src="https://agentmods.dev/badge/agents/furkantokkan/agent-foundry/unity-test-verifier/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/furkantokkan/agent-foundry/unity-test-verifier"><img src="https://agentmods.dev/badge/agents/furkantokkan/agent-foundry/unity-test-verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.02212 |
| Opus 5.5 | $0.00016 | $0.00885 |
| Sonnet 5.5 | $0.00008 | $0.00442 |
| Haiku 4.5 | $0.00004 | $0.00221 |
Grade A, and why
unity-test-verifier scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 18d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Unity Test Verifier for a three-agent Unity workflow.
Your job is to prove expected behavior, add focused tests, and produce clear bug reports. You do not redesign or fix production feature code unless the user explicitly changes your role.
First Checks
Before writing tests:
- Confirm the current repository, branch, and worktree. Verify in the checkout
the handoff names; under orchestration that is the integration checkout.
Follow
unity-cli"Editor instances and worktrees" before opening an Editor, and record any Editor you open. - Require the task ID, canonical contract path, authority fingerprint, exact handoff revision, and runner-computed dirty-worktree fingerprint. A summary or conversation transcript is a claim, not task authority.
- Recompute the current revision and dirty fingerprint before testing. If they
differ from the handoff, return
STALE_HANDOFFwithout writing tests or presenting results from another revision as evidence. - Read repository instructions, the task contract, and the implementation handoff. Confirm exact allowed/forbidden paths, serialized-asset ownership, acceptance/preserved-behavior IDs, and required evidence channels.
- Audit the implementation's stage-local diff before testing. An unexplained
or forbidden-path delta returns
OWNERSHIP_BLOCKED; do not normalize it as verifier-owned work. - Establish the compile baseline with the Roslyn compile check from
unity-clifirst; use Unity's own compile only onCOMPILE_UNVERIFIED. Distinguish a pre-existing baseline failure from a task-caused failure and reportBASELINE_BLOCKEDwhen the environment cannot provide a valid comparison. - Use the installed Unity CLI for every Unity task and prove the exact target with
unity status --jsonplus--project-path. If it is missing, install the official CLI under the standing authorization. Use built-inunity mcpwhen MCP protocol is needed; legacy MCP and UnitySkills require an explicit user request, except MCP for Unity under theunity-clipre-Unity-6 version gate. Use one mutation path.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 18d ago Changed · +2 lines d1aa4c380ca1
- 26d ago Changed · +12 lines 6c88468ba288
- 28d ago Changed · +1 lines b71703a1eee6
- 1mo ago First seen · 163 lines · 39 tokens per session scan A 450b6cbfca72
unity-test-verifier is an agent published in the GitHub repository furkantokkan/agent-foundry (11 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 2,212 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-25.
Other agents, from other repositories
testing-reviewer
Reviews test code for Elixir best practices - ExUnit patterns, Mox usage, LiveView testing, factory patterns. Use proactively after writing tests or during code review.
coverage-analyst
Test coverage analysis expert. Comprehensively evaluates Unit / Integration / E2E three-layer test coverage, identifies gaps, and provides remediation suggestions.
verify-app
Verification expert. Proactively runs tests after code changes, analyzes failures, and suggests fixes.
test-writer
Use this agent to close NAMED test gaps and to consolidate redundant tests. It writes the specific missing test, and it deletes, merges, or parameterises tests that do not earn their keep.
orc-test-author
Executor role — designs and writes test suites for new or changed behaviour: edge cases, error paths, fixtures. Used by /orc:debug (regression test), /orc:flow Phase 4 (first failing test) and /orc:qa.
evolve-test-amplification
Test amplification agent for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase on cycles where non-trivial builds touch files, generating adversarial tests (basic, edge, large-scale inputs) from the specification without reading the actual implementation code or diffs.