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.
npx skills add Kastalien-Research/thoughtbox --skill test-suitegit clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWrote 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/skills/kastalien-research/thoughtbox/test-suite)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/test-suite"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/test-suite/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/skills/kastalien-research/thoughtbox/test-suite"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/test-suite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.01213 |
| Opus 5.5 | $0.00020 | $0.00485 |
| Sonnet 5.5 | $0.00010 | $0.00243 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
test-suite 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 1mo 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thoughtbox Code Mode Behavioral Test Suite
Run behavioral tests against a live Thoughtbox MCP server whose public surface is Code Mode.
The authoritative hosted contract is:
thoughtbox_searchthoughtbox_executethoughtbox_peer_notebook
The legacy progressive-disclosure suite (thoughtbox_init, thoughtbox_operations, raw per-domain tools) is no longer the primary behavioral contract for /mcp. Treat the old 01-09 markdown files in this folder as historical reference only unless you are explicitly auditing legacy behavior.
Test Files
| # | File | Focus | Tests |
|---|---|---|---|
| 01 | tests/01-codemode-surface.md |
Public MCP surface and instructions | 4 |
| 02 | tests/02-codemode-search.md |
Search catalog discovery | 5 |
| 03 | tests/03-codemode-thought.md |
Thought workflows: all types, branching, revision, agents | 15 |
| 04 | tests/04-codemode-sessions.md |
Session CRUD, search, resume, export, analysis | 8 |
| 05 | tests/05-codemode-knowledge.md |
Knowledge graph: entities, relations, traversal | 5 |
| 06 | tests/06-codemode-protocols.md |
Theseus, Ulysses, and observability lifecycles | 8 |
| 07 | tests/07-hub.md |
Hub coordination via tb.hub.*: identity, workspaces, problems, proposals, consensus, channels |
15 |
Total: 60 behavioral tests across the 3-tool Code Mode surface
Every test creates real data in Supabase and verifies it through retrieval. The suite should leave named sessions visible in the web app's Runs view.
How to Run
Step 1: Verify the server is running
Confirm the live MCP server is reachable and using the Code Mode surface:
- Connect to the server.
- Call
tools/list. - Verify the tool list is exactly:
thoughtbox_searchthoughtbox_executethoughtbox_peer_notebook
If raw tools like thoughtbox_init, thoughtbox_session, or thoughtbox_hub appear in tools/list, the behavioral suite should fail immediately because the hosted surface is not the intended Code Mode contract.
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- tests/01-codemode-surface.md 1.7 KB
- tests/01-init.md 3.3 KB
- tests/02-codemode-search.md 1.9 KB
- tests/02-operations.md 2.3 KB
- tests/03-codemode-thought.md 12 KB
- tests/03-session.md 4.8 KB
- tests/04-codemode-sessions.md 4.3 KB
- tests/04-knowledge.md 5.8 KB
- tests/05-codemode-knowledge.md 3.3 KB
- tests/05-thought.md 9.3 KB
- tests/06-codemode-protocols.md 6.4 KB
- tests/06-notebook.md 3.3 KB
- tests/07-hub.md 9.4 KB
- tests/08-theseus.md 3.0 KB
- tests/09-ulysses.md 4.2 KB
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.
- 1mo ago First seen · 130 lines · 51 tokens per session scan A a3fe3a3e314b
test-suite is a skill published in the GitHub repository Kastalien-Research/thoughtbox (65 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 1,213 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 2026-08-30.
Other skills, from other repositories
review-ugc-render
Mandatory pre-publish review gate for a UGC video render. Transcribes the finished render's AUDIO with Whisper and word-diffs it against the approved spoken script, then gates keeping the render as the final version (videoreview) — blocking a render whose generated audio mis-voices a word (e.g. the approved…
ios-simulator-skill
Build, test, and drive iOS apps in the Simulator with 30 token-efficient scripts. Use when asked to build or test an Xcode project, launch an app on a simulator, tap/type/swipe through its UI by accessibility label, take screenshots or visual diffs, audit accessibility, read logs or diagnose hangs, or manage…
f1-test-drive
Assess F1 applicability, then validate changed product workflows or the F1 harness end-to-end. Skip drives and reports when no relevant workflow behavior changes.
add-test
Scaffold a test file for an existing tool, resource, or service. Use when the user asks to add tests, improve coverage, or when a definition exists without a matching test file.
opik-test
Turn a failing Opik trace (or a described failure) into a repeatable regression check — a test-suite item with the trace's input and one or two binary assertions — so a fix can be verified by the compare skill. Works over the SDK; uses the MCP write tool when connected. Returns the suite, the item, and the assertion.…
unity-testability
Advise on Unity testability.