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/profiles-tdd)<a href="https://agentmods.dev/commands/kastalien-research/thoughtbox/profiles-tdd"><img src="https://agentmods.dev/badge/commands/kastalien-research/thoughtbox/profiles-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/profiles-tdd"><img src="https://agentmods.dev/badge/commands/kastalien-research/thoughtbox/profiles-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 | $0.00029 | $0.03421 |
| Opus 5.5 | $0.00012 | $0.01368 |
| Sonnet 5.5 | $0.00006 | $0.00684 |
| Haiku 4.5 | $0.00003 | $0.00342 |
Grade A, and why
profiles-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 — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/profiles-tdd
Strict TDD workflow for implementing hierarchical agent roles (SPEC-HUB-002). Profiles bind mental models to agent identities, enabling behavioral specialization. Follows the same TDD discipline as /hub-tdd and /multi-agent-tdd.
Variables
RESUME: $ARGUMENTS (default: auto-detected from .profiles-tdd/state.json)
Module Order (dependency-driven)
| # | Module | Test Count | Type | Depends On | Files |
|---|---|---|---|---|---|
| 1 | profile-types | 0 | Pure types | — | new src/hub/profiles-types.ts, mod src/hub/hub-types.ts |
| 2 | profiles-registry | 8 | New (TDD) | M1 | new src/hub/profiles-registry.ts |
| 3 | identity-profiles | 6 | Hybrid | M1, M2 | mod src/hub/identity.ts |
| 4 | profile-prompt | 5 | New (TDD) | M2 | mod src/hub/hub-handler.ts |
| 5 | thought-priming | 7 | New (TDD) | M2, M4 | new src/hub/profile-primer.ts, mod src/gateway/gateway-handler.ts |
| 6 | hub-integration | 6 | Integration | M1–M5 | test file only |
| Total | 32 |
Expected Test Counts Per Module
{
"profiles-registry": { "count": 8, "ids": "T-PR2-1..8", "files": ["profiles-registry.test.ts"] },
"identity-profiles": { "count": 6, "ids": "T-IP-1..6", "files": ["identity-profiles.test.ts"] },
"profile-prompt": { "count": 5, "ids": "T-PP-1..5", "files": ["profile-prompt.test.ts"] },
"thought-priming": { "count": 7, "ids": "T-TP-1..7", "files": ["thought-priming.test.ts"] },
"hub-integration": { "count": 6, "ids": "T-PI-1..6", "files": ["profiles-integration.test.ts"] }
}
Profile Definitions (authoritative)
| Profile | Mental Models | Primary Goal |
|---|---|---|
| MANAGER | decomposition, pre-mortem, five-whys | Delegation and team coordination |
| ARCHITECT | decomposition, trade-off-matrix, abstraction-laddering | Structural design |
| DEBUGGER | five-whys, rubber-duck, assumption-surfacing | Root cause analysis |
| SECURITY | adversarial-thinking, pre-mortem | Risk and vulnerability detection |
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 · 382 lines · 29 tokens per session scan A 3a26e339db13
profiles-tdd is a command published in the GitHub repository Kastalien-Research/thoughtbox (66 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 3,421 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.