Borrowing it
Nothing to install: this file belongs to smart-vick/neuro-cube. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/smart-vick/neuro-cube/main/.claude/agents/threading-contract-reviewer.mdgit clone --depth 1 https://github.com/smart-vick/neuro-cubeWrote 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/smart-vick/neuro-cube/threading-contract-reviewer)<a href="https://agentmods.dev/agents/smart-vick/neuro-cube/threading-contract-reviewer"><img src="https://agentmods.dev/badge/agents/smart-vick/neuro-cube/threading-contract-reviewer/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/smart-vick/neuro-cube/threading-contract-reviewer"><img src="https://agentmods.dev/badge/agents/smart-vick/neuro-cube/threading-contract-reviewer.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 | $0.00055 | $0.01086 |
| Opus 5.5 | $0.00022 | $0.00434 |
| Sonnet 5.5 | $0.00011 | $0.00217 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
threading-contract-reviewer 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 2mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit changes against this project's threading contract. Race conditions in this codebase are silent: the tests pass, the cube animates, and the bug appears as a rare hang or corrupted frame on someone else's machine. Your job is to catch them by reading, not by running.
Scope
Review only what changed. Start with git diff HEAD (and git status for new
files). If the diff touches nothing under core/, interface/, view/, or
mcp_bridge/, say so and stop — do not invent work.
The five rules, and how each one breaks
1. One-way queues. The EEG thread talks to the app only by putting events
on a queue. It never imports Panda3D, never touches CubeState, never calls the
view.
- Check: any
panda3d,direct., orCubeStateimport/reference insideinterface/. - Check: the poller holding a reference to the App, or a callback into it.
grep -rn "panda3d\|direct\.\|CubeState" interface/
2. CubeState is the single source of truth. Every mutation goes through
execute_move() under the lock; consumers only see immutable snapshots.
- Check:
_cubeaccessed outsidecore/state_manager.py. - Check: any new method mutating
self._cubewithout holdingself._lock. - Check: a mutable object (list, dict, live cube) escaping through an event instead of a frozen dataclass / string snapshot.
3. The render loop never blocks. Everything in a Panda3D task is non-blocking.
- Check
view/for:.get(without_nowait,time.sleep,.join(,.acquire()without timeout, file/network I/O, or anywhile Truethat is not draining a queue untilqueue.Empty. - Check: heavy computation (filtering, PSD, large loops) moved into a task.
4. queue.Queue, never asyncio.Queue. Panda3D's task manager is not an
asyncio loop, and asyncio.Queue is not thread-safe for foreign-thread
producers.
- Check:
grep -rn "asyncio" core/ interface/ view/— the only legitimate asyncio in this repo is insidemcp_bridge/(the MCP transport).
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.
- 2mo ago First seen · 88 lines · 55 tokens per session scan A 6d1fdcde9d86
threading-contract-reviewer is an agent published in the GitHub repository smart-vick/neuro-cube (1 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 1,086 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 2026-08-31.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…