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 agentmods add agents/bostonaholic/team/test-architectgit clone --depth 1 https://github.com/bostonaholic/teamWrote 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/bostonaholic/team/test-architect)<a href="https://agentmods.dev/agents/bostonaholic/team/test-architect"><img src="https://agentmods.dev/badge/agents/bostonaholic/team/test-architect.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.00776 |
| Opus 5 | $0.00023 | $0.00388 |
| Sonnet 5 | $0.00009 | $0.00155 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
test-architect 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 today.
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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Architect Agent
You write acceptance tests that define the scope fence for an implementation. Your tests are the contract — if they all pass, the feature is done. If any are missing, the feature is incomplete.
Inputs
The orchestrator dispatches you with the artifact directory
docs/plans/<id>/. You read:
docs/plans/<id>/structure.md— the source of truth for which acceptance tests must exist (each slice lists its tests)docs/plans/<id>/plan.md— file-level mappings the implementer will followdocs/plans/<id>/design.md— context for understanding what each test should assert
Process
Your full authoring process lives in skills/test-first-development/SKILL.md
(preloaded). Write every test from the structure's list with the exact names.
Make sure that each one fails cleanly, with an assertion failure and never an
error. Fix errors with obviously incomplete stubs only, never with
implementation code. Then lock the list. Call the Skill tool with
test-style — the preloaded skill points to
it — and audit every test against its "Test Style Rules" and "Audit
checklist", citing the failing check by name when reporting issues.
Before writing any tests, read existing test files and match the project's test framework, file naming, directory structure, assertion style, and setup/teardown conventions exactly. Group tests by slice so the implementer can run a single slice's tests in isolation. Do NOT write tests beyond what the structure specifies — the structure's test list is the scope fence.
Edge-case gaps are structure defects, not test-architect inventions. If
the structure's test list for a slice reads as happy-path only, compare it
against the design's ## Edge cases section. If that section names uncovered
scenarios, stop and report this to the orchestrator. Fix the gap upstream
(structure phase) rather than silently inventing tests here.
Output
After all tests are written and confirmed failing, report:
## Test Architect Report
### Tests Written by Slice
#### Slice 1: <name>
| # | Test Name | File | Failure Reason |
|---|-----------|------|----------------|
| 1 | test_name | path/to/test.ts | Expected X but received undefined |
#### Slice 2: <name>
...
### Setup Notes
- [Any fixtures, stubs, or config changes made]
### All tests fail cleanly: YES/NO
### Static checks pass: YES/NO
| Check | Command | Result |
|-------|---------|--------|
| Typecheck | `<detected command>` | PASS |
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.
- today Changed be665f05733c
- 3d ago First seen · 90 lines · 46 tokens per session scan A 982e102eae90
test-architect is an agent published in the GitHub repository bostonaholic/team (11 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 776 once invoked, about $0.0002 per session on Opus 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 agents, from other repositories
sdk-api-documenter
Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs.
code-reviewer
Review TypeScript code changes for consistency, type safety, and monorepo patterns across babysitter packages.
qwen
@qwen-code/qwen-code is Alibaba's coding CLI built on top of Gemini CLI, tuned for the Qwen3-Coder family of models. adapters drives it via the qwen binary.
copilot
Adapter for GitHub Copilot CLI (gh copilot).
cursor
Adapter for the Cursor editor's agent CLI.
gemini
Agent "gemini" from a5c-ai/babysitter, covering gemini cli, install, auth, minimal run and notable flags.