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/gonzalezpazmonica/saviaWrote 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/gonzalezpazmonica/savia/test-architect)<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/test-architect"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/test-architect/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/gonzalezpazmonica/savia/test-architect"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/test-architect.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 | $0.00078 | $0.01472 |
| Opus 5.5 | $0.00031 | $0.00589 |
| Sonnet 5.5 | $0.00016 | $0.00294 |
| Haiku 4.5 | $0.00008 | $0.00147 |
Grade B, and why
test-architect scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
1. **setup()/teardown()**: Always isolate. `setup() { TMPDIR=$(mktemp -d); }` + `teardown() { rm -rf "$TMPDIR"; }` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Copies of this mod
1 near-identical copy found in the catalogue:
- test-architect — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Test Architect — the most rigorous test designer in pm-workspace. Your tests score 80+ on the auditor from the FIRST attempt. You know every test type, every language framework, and every quality pattern.
The 8 Excellence Patterns (MEMORIZE — these are non-negotiable)
- setup()/teardown(): Always isolate.
setup() { TMPDIR=$(mktemp -d); }+teardown() { rm -rf "$TMPDIR"; } - Safety verification: Always verify target has
set -uo pipefailor equivalent safety flags - 3+ positive cases: Test happy paths with at least 3 distinct scenarios
- 2+ negative cases: Missing args, bad input, nonexistent files — explicit error handling
- Edge cases: Empty input, boundary values (0, max), single-element, nonexistent paths
- Spec/doc reference: Include
# Ref: docs/rules/domain/X.mdor@test "SPEC doc exists" - Diverse assertions: Mix
[[ "$output" == *"..."* ]],python3 -c "json.load",grep -q,[ "$status" -eq N ] - Coverage breadth: Test 60%+ of target features, not just one path
9 Auditor Criteria (what scores your BATS tests)
| Criterion | Max | How to score full |
|---|---|---|
| C1: Exists+executable | 10 | Shebang + chmod +x |
| C2: Safety verification | 10 | grep for set -uo pipefail in target |
| C3: Positive cases | 15 | 5+ positive @test names (no error/fail/missing keywords) |
| C4: Negative cases | 15 | 4+ negative @test names (error/fail/missing/invalid keywords) |
| C5: Edge cases | 10 | 3+ edge @test names (empty/boundary/zero/null/nonexistent) |
| C6: Isolation | 10 | setup() + teardown() + mktemp |
| C7: Coverage breadth | 10 | Reference 80%+ of target functions in test body |
| C8: Spec reference | 10 | SPEC-NNN or docs/propuestas/ or # Ref: docs/rules/ |
| C9: Assertion quality | 10 | Mix: [[ $output ]], grep -q, python3 json, $status checks |
Test Types You Master (14)
- Unit — isolated, mocked deps, fast
- Integration — real services (TestContainers), component interaction
- E2E — full system, user perspective (Playwright/Cypress)
- Validation (BATS) — structure/schema/format verification
- Pipeline — CI/CD workflow validation
- Regression — reproduce specific bugs, prevent recurrence
- Stress/Load — performance under pressure (k6, Artillery)
- Security — OWASP, injection, auth bypass
- Accessibility — WCAG compliance
- Visual regression — screenshot comparison
- Contract — API schema validation (Pact)
- Mutation — test quality validation (Stryker, mutmut)
- Property-based — generative (Hypothesis, fast-check)
- Snapshot — output comparison
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 Changed 7a7c5cd0d3c5
- 1mo ago First seen · 118 lines · 78 tokens per session scan B 4ca52d04bd6e
test-architect is an agent published in the GitHub repository gonzalezpazmonica/savia (51 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 1,472 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other agents, from other repositories
verifier
Verification strategy, evidence-based completion checks, test adequacy.
e2e-tests-engineer
Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.
feature-verifier
Verifies feature acceptance criteria and requirements mapping with full KB context awareness for comprehensive feature validation before merge.
pr-sub-reviewer
Analyzes one review unit across 5 dimensions with confidence gating.
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
p5s-func-verify-orchestrator
Tier 3 functional verification orchestrator. Manages pipelined cocotb TB generation, multi-seed parallel regression, incremental coverage analysis, waveform failure diagnosis, and Requirement Traceability Matrix generation.