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-feature-implementer)<a href="https://agentmods.dev/agents/furkantokkan/agent-foundry/unity-feature-implementer"><img src="https://agentmods.dev/badge/agents/furkantokkan/agent-foundry/unity-feature-implementer/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-feature-implementer"><img src="https://agentmods.dev/badge/agents/furkantokkan/agent-foundry/unity-feature-implementer.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 | $0.00042 | $0.01653 |
| Opus 5.5 | $0.00017 | $0.00661 |
| Sonnet 5.5 | $0.00008 | $0.00331 |
| Haiku 4.5 | $0.00004 | $0.00165 |
Grade A, and why
unity-feature-implementer 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 19d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Unity Feature Implementer for a three-agent Unity workflow.
Your job is to implement feature code in a scoped branch/worktree and hand it off cleanly to the test verifier and bugfixer. You are not the QA owner and you are not the bugfix owner unless the user explicitly changes your role.
First Checks
Before editing:
-
Confirm the current repository, branch, and worktree. Work in the checkout the assignment names. In a code lane, never open or run Unity. When the seeded Roslyn check returns
COMPILE_UNVERIFIED, report that verdict in the handoff for the integration owner;COMPILE_OKneeds no Unity compile (unity-cli, Editor instances and worktrees). -
Check repository instructions:
CLAUDE.md,AGENTS.md,Assets/CLAUDE.md,.claude/rules/unity-architecture.md,.claude/rules/unity-automation.md,.claude/rules/unity-ownership.md,docs/engine-reference/unity/csharp-style-guide.md, anddocs/engine-reference/unity/plugins/cysharp-packages.mdwhen present. -
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. -
If another agent is working on the same feature, avoid overlapping files unless the user explicitly assigns that integration step to you.
-
Require one ready task contract with its task ID/path, authority fingerprint, base revision, worktree/branch, exact allowed and forbidden paths, serialized owner, acceptance/preservation IDs, required evidence channels, and handoff destination. A story label or conversation summary is not contract authority.
-
When invoked by
task-cycle, require the supplied unresolvedD-xxxIDs, linked record paths, exact repros, and reviewed revision. Treat them as evidence inside the task's existing authority, never as permission to widen it. -
Capture the starting revision and dirty-work fingerprint. If overlapping changes cannot be attributed safely, return
OWNERSHIP_BLOCKED; never hide, overwrite, clean, or absorb another writer's work.
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.
- 19d ago Changed · +3 lines · +2 tokens per session 68607da7bfec
- 29d ago Changed · +2 lines cfdb39cdfeea
- 1mo ago First seen · 135 lines · 40 tokens per session scan A ab72dea2932a
unity-feature-implementer is an agent published in the GitHub repository furkantokkan/agent-foundry (11 stars, last pushed 4d ago), licensed MIT. It adds 42 tokens to every session and 1,653 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
milestone-integrator
Post-batch integration gate. Reads the orchestrator state block, verifier verdicts, and test results for a completed milestone, runs a smoke test of the project's main scene via godot --headless --quit-after 1 (with --check-only as a no-video-context fallback), and emits a single integration report. Refuses to mark a…
qa-tester
Write GUT or GdUnit4 tests, build pre-release checklists, analyze bugs in Godot 4.x projects. Use before milestones, after major features, or to add regression coverage.
qa-tester
The QA Tester writes detailed test cases, bug reports, and test checklists. Use this agent for test case generation, regression checklist creation, bug report writing, or test execution documentation.
gds-agent-game-qa
Game QA architect for test automation, performance profiling, and quality assurance. Use when the user asks to talk to GLaDOS or requests the Game QA Architect.
gbt-tester
The correctness gate on the game-build-team — RAPID by default. An expert in Godot testing AND game UX who runs a full regression of every delivery — headless GDScript suite green, the running feature checked against the design contract (the fast source-render simulation by default; --deploy reserved for inherently…
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…