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/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/commands/kastalien-research/thoughtbox/hub-tdd)<a href="https://agentmods.dev/commands/kastalien-research/thoughtbox/hub-tdd"><img src="https://agentmods.dev/badge/commands/kastalien-research/thoughtbox/hub-tdd/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/commands/kastalien-research/thoughtbox/hub-tdd"><img src="https://agentmods.dev/badge/commands/kastalien-research/thoughtbox/hub-tdd.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 | $0.00027 | $0.04113 |
| Opus 5.5 | $0.00011 | $0.01645 |
| Sonnet 5.5 | $0.00005 | $0.00823 |
| Haiku 4.5 | $0.00003 | $0.00411 |
Grade A, and why
hub-tdd 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 — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hub-tdd
Strict TDD workflow for implementing the MCP Hub from ADR-002. Enforces: types first, then tests (must be red), then implementation (must be green), with git commits at every checkpoint.
Variables
RESUME: $ARGUMENTS (default: auto-detected from .hub-tdd/state.json)
Module Order (dependency-driven)
| # | Module | Test Count | Depends On |
|---|---|---|---|
| 0 | hub-types | 0 (pure types) | — |
| 1 | identity | 4 | hub-types |
| 2 | attribution | 3 | hub-types, existing ThoughtData |
| 3 | workspace | 6 | identity |
| 4 | problems | 7 | workspace |
| 5 | proposals | 10 | problems |
| 6 | consensus | 5 | workspace |
| 7 | channels | 9 | problems |
| 8 | proxy | 5 | hub-handler interface |
| 9 | hub-handler | 18 | all modules |
| 10 | integration | 3 | everything |
| Total | 70 |
Expected Test Counts Per Module
These counts are authoritative (derived from ADR Section 10 test IDs):
{
"identity": { "count": 4, "ids": "T-ID-1..4", "files": ["identity.test.ts"] },
"attribution": { "count": 3, "ids": "T-ATT-1..3", "files": ["attribution.test.ts"] },
"workspace": { "count": 6, "ids": "T-WS-1..6", "files": ["workspace.test.ts"] },
"problems": { "count": 7, "ids": "T-PR-1..7", "files": ["problems.test.ts"] },
"proposals": { "count": 10, "ids": "T-PP-1..10", "files": ["proposals.test.ts"] },
"consensus": { "count": 5, "ids": "T-CON-1..5", "files": ["consensus.test.ts"] },
"channels": { "count": 9, "ids": "T-CH-1..5, T-CHSUB-1..4", "files": ["channels.test.ts", "channel-subscription.test.ts"] },
"proxy": { "count": 5, "ids": "T-PX-1..5", "files": ["proxy.test.ts"] },
"hub-handler": { "count": 18, "ids": "T-PD-1..3, T-ERR-1..6, T-TERM-1..4, T-ISO-1..4, T-STOR-1..5", "files": ["hub-handler.test.ts", "errors.test.ts", "terminal-state.test.ts", "isolation.test.ts", "storage.test.ts"] },
"integration": { "count": 3, "ids": "T-INT-1, T-CONC-1..2", "files": ["integration.test.ts", "concurrent.test.ts"] }
}
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 · 444 lines · 27 tokens per session scan A 9e9f831ba5a9
hub-tdd is a command published in the GitHub repository Kastalien-Research/thoughtbox (66 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 4,113 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
start
Start a new pair programming session with AI assistance.
tdd
Test-driven development with TodoWrite planning and comprehensive testing.
usage-add
PitWay: Accumulate measured planning or qa token usage onto a milestone.
complete
Complete a partially implemented feature by filling gaps and ensuring production readiness.
tdd
A command that follows test-driven development (TDD), a method where you write tests before the code they check. It moves through writing a failing test, adding the smallest implementation, and then improving the code.
dashboard
Generar dashboard HTML local con métricas de eficiencia del proyecto SDD.