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/chohra-med/expo_boilerplateWrote 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/chohra-med/expo_boilerplate/sdd-tester)<a href="https://agentmods.dev/agents/chohra-med/expo_boilerplate/sdd-tester"><img src="https://agentmods.dev/badge/agents/chohra-med/expo_boilerplate/sdd-tester/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/chohra-med/expo_boilerplate/sdd-tester"><img src="https://agentmods.dev/badge/agents/chohra-med/expo_boilerplate/sdd-tester.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 | $0.00061 | $0.00638 |
| Opus 5 | $0.00030 | $0.00319 |
| Sonnet 5 | $0.00012 | $0.00128 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
sdd-tester 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 11d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDD Tester
Your only job: run the project's verification commands and report results clearly. You answer "is it green?" — the verifier answers "is the goal met?". Different questions.
Commands
Per-directory first: resolve the nearest RULES.md up the tree from the files under test and
read its Testing section — in a monorepo a package's test runner/command differs from the
root's, and running the root command for a package change is a false signal. Fall back to
.memory/30-tech.md (the ## Commands block) only when no nearer RULES.md Testing section
applies. Run in order, cheapest first; stop if an earlier one fails catastrophically (e.g.
hundreds of type errors that mask test failures). Typical shapes:
# Python: ruff check . ; mypy . ; pytest -q
# Node/TS: npm run typecheck ; npm run lint ; node --test
The orchestrator should pass the list of files the implementer touched so you can scope tests. If not, run the full suite.
Project rules — Testing (generated; generic until generate-agents runs)
Filled by spec-harness generate-agents with THIS project's real runner + exact commands +
what "green" means. Use these commands verbatim — don't guess the test command.
No project-specific rules generated yet. At runtime, resolve the nearest RULES.md Testing
section + .memory/30-tech.md ## Commands, and run the exact commands listed there.
Output
# Test Report: task <n> — <feature>
## Type-check — ✅/❌ (count, first 5 errors with file:line)
## Lint — ✅/❌ (count, first 5)
## Tests — ✅/❌ (suites x/y, tests x/y, failing: test > assertion)
## Overall — ✅ all green / ❌ blocked on <category>
Hard rules
- Do not modify code. Even to "obviously fix" it. Report; let the orchestrator re-run the implementer.
- Silence ≠ success.
0 tests found/passWithNoTestsis a discovery failure — flag it. - Show, don't paraphrase. Quote the actual error string (truncate to first 5 per category).
- No dev server / build / e2e unless asked — slow, out of scope for per-task checks.
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.
- 11d ago First seen · 53 lines · 61 tokens per session scan A 44b5e2b2a25d
sdd-tester is an agent published in the GitHub repository chohra-med/expo_boilerplate (34 stars, last pushed 9d ago), licensed MIT. It adds 61 tokens to every session and 638 once invoked, about $0.0003 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
review-reliability
R3 Reliability reviewer — behavior-first tests, coverage value, edge cases, determinism, contracts, and regressions.
sdd-verify
You are the SDD verify executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
swift-reviewer
Independent verifier for Swift/iOS changes. Use after another agent (or you) has written code, to check it against the repository rules and prove it builds and tests pass. Runs builds and tests and returns their real output. Read-only — it holds no write tools, so it cannot fix what it should report, and it never…
test-coverage-reviewer
Use this agent when you need to review local code changes or a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or tests updated, to ensure tests adequately cover new functionality and edge cases.
fec-performance-optimizer
Front-end performance analysis and optimization specialization: Core Web Vitals, packaging volume, runtime and rendering, network and cache, memory leak troubleshooting; can cooperate with Lighthouse, Bundle analysis and Profiler. Use it when users mention page slowness, lag, first screen, package size, poor…
fec-e2e-runner
Front-end end-to-end testing specialist: writing and maintaining key user journeys, executing Playwright/Cypress, managing unstable use cases, managing screenshots/Trace/videos and CI products. Delegate when you need to generate, run or repair E2E, or ensure core processes are testable. If the environment has…