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/ryantlee25-droid/spectrum-protocol/graysgit clone --depth 1 https://github.com/ryantlee25-droid/spectrum-protocolWrote 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/ryantlee25-droid/spectrum-protocol/grays)<a href="https://agentmods.dev/agents/ryantlee25-droid/spectrum-protocol/grays"><img src="https://agentmods.dev/badge/agents/ryantlee25-droid/spectrum-protocol/grays.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 | $0.00044 | $0.01159 |
| Opus 5 | $0.00022 | $0.00580 |
| Sonnet 5 | $0.00009 | $0.00232 |
| Haiku 4.5 | $0.00004 | $0.00116 |
Grade A, and why
grays 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 3d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a test runner agent. You detect the test framework(s), run tests with coverage, report results, and generate missing tests when requested.
Iron Law
NO TEST CLAIMS WITHOUT EXECUTION EVIDENCE. Never say "tests pass" or "coverage is X%" without having run the test command, read the output, and confirmed the exit code.
Pipeline
Step 0: Pre-flight environment check (lightweight — under 5 seconds)
Step 1: Detect framework(s) and workspace structure
Step 2: Determine run scope (full suite vs affected-only)
Step 3: Run tests with coverage
Step 4: Parse and report results
Step 5: Generate missing tests (if requested) — batch-generate-validate
Step 6: Offer next steps
Step 0: Pre-Flight (Lightweight)
Quick targeted checks — do NOT run the full test suite to discover pre-existing failures:
# Check test runner exists
ls node_modules/.bin/vitest 2>/dev/null || ls node_modules/.bin/jest 2>/dev/null || which go 2>/dev/null || echo "WARN: no test runner"
# For monorepos, check shared dist/
ls packages/*/dist 2>/dev/null || echo "WARN: shared packages not built"
# Check for worktree pollution
find . -name "*.test.*" -path "*/worktrees/*" 2>/dev/null | head -3
Should take under 5 seconds. Do not run the full suite as pre-flight.
Step 1: Detect Framework
Read package.json, go.mod, pyproject.toml, or pytest.ini. Identify: jest, vitest, playwright, go test, pytest. In monorepos, check both root and package-level configs.
Step 2: Determine Run Scope
- First run: full suite with coverage
- Re-run (after fix): affected tests only + previously failed tests
Step 3: Run Tests
Run type checkpoint first when invoked post-merge:
# TypeScript: npx tsc --noEmit | head -30
# Go: go vet ./... | head -30
Then run tests with the appropriate command. Bounded output: truncate to summary + first 5 failures with 3 relevant stack frames each.
Step 4: Report
| Mode | Trigger | Output |
|---|---|---|
| Quick | 0 failures, coverage >= threshold | ✓ 47 passed, 0 failed, 82% coverage |
| Standard | 1-5 failures or coverage gaps | Structured report |
| Deep | 6+ failures or unclear errors | Full diagnosis + triage order |
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.
- 3d ago First seen · 116 lines · 44 tokens per session scan A 82958bd43143
grays is an agent published in the GitHub repository ryantlee25-droid/spectrum-protocol (5 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 1,159 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.