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/yaleh/meta-cc/agent-validation-buildergit clone --depth 1 https://github.com/yaleh/meta-ccWhat 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 | $0.00024 | $0.02609 |
| Opus 5 | $0.00012 | $0.01305 |
| Sonnet 5 | $0.00005 | $0.00522 |
| Haiku 4.5 | $0.00002 | $0.00261 |
Grade A, and why
agent-validation-builder 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 2d 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 — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
λ(target, conventions) → validation_tool | ∀validator ∈ validators:
build :: (Target, Conventions) → Validation_Tool build(T, C) = design_types() → implement_parser(T.format) → create_validators(C) → build_reporter() → integrate_cli() → add_tests() → document() → integrate_workflow() → continuous_improvement()
design_types :: () → Type_System design_types() = { Tool: {name: string, description: string, parameters: [Parameter]}, Parameter: {name: string, type: string, description: string, required: bool}, ValidationResult: {tool_name: string, check_name: string, passed: bool, message: string, severity: string, details: map}, Report: {total_tools: int, total_checks: int, passed: int, failed: int, warnings: int, results: [ValidationResult]},
return {Tool, Parameter, ValidationResult, Report} }
implement_parser :: Format → Parser implement_parser(format) = { parser: match format with | "json_schema" → regex_parser(), # MVP: Fast, simple | "openapi" → ast_parser(), # Production: Robust | "graphql" → ast_parser(), | _ → custom_parser(),
regex_parser: { tool_pattern: "Name:\s*"([^"]+)"", desc_pattern: "Description:\s*"([^"]+)"", param_pattern: ""([^"]+)":\s*{[^}]Type:\s"([^"]+)"", extract: λcontent → match_all(patterns, content) },
ast_parser: { parse: "go/parser.ParseFile(file)", traverse: "ast.Inspect(node, visitor)", extract: λnode → extract_tool_definitions(node) },
return parser }
create_validators :: Conventions → Validators create_validators(C) = { validators: [],
∀convention ∈ C → validator: match convention with | "naming_convention" → create_naming_validator(), | "parameter_ordering" → create_ordering_validator(), | "description_format" → create_description_validator(), | _ → create_custom_validator(convention),
validators += validator,
return validators }
create_naming_validator :: () → Validator create_naming_validator() = { pattern: "^[a-z][a-z0-9_]*$", # snake_case
check: λtool → { if ¬matches(tool.name, pattern) then { tool_name: tool.name, check_name: "naming_convention", passed: false, message: "Tool name '" + tool.name + "' violates naming convention", severity: "ERROR", details: { suggestion: "Use snake_case format", expected: "snake_case_pattern", actual: tool.name, reference: "docs/api-naming-convention.md" } } else {tool_name: tool.name, check_name: "naming_convention", passed: true, severity: "INFO"} } }
create_ordering_validator :: () → Validator create_ordering_validator() = { tier_system: TierDefinitions,
check: λtool → { categorized: categorize_parameters(tool.parameters, tier_system), expected_order: sort_by_tier(categorized), actual_order: tool.parameters,
matches: ∀i ∈ [0..|expected_order|] → expected_order[i].name = actual_order[i].name,
if ¬matches then
{
tool_name: tool.name,
check_name: "parameter_ordering",
passed: false,
message: "Parameters not in tier order",
severity: "ERROR",
details: {
suggestion: "Reorder parameters by tier (1→2→3→4→5)",
expected: [p.name | p ∈ expected_order],
actual: [p.name | p ∈ actual_order],
reference: "docs/api-parameter-convention.md"
}
}
else
{tool_name: tool.name, check_name: "parameter_ordering", passed: true, severity: "INFO"}
} }
create_description_validator :: () → Validator create_description_validator() = { required_pattern: "Default scope:",
check: λtool → { if ¬contains(tool.description, required_pattern) then { tool_name: tool.name, check_name: "description_format", passed: false, message: "Missing required pattern: '" + required_pattern + "'", severity: "WARNING", details: { suggestion: "Add '" + required_pattern + " ' to description", expected: "Description with scope declaration", actual: tool.description, reference: "docs/api-consistency-methodology.md" } } else {tool_name: tool.name, check_name: "description_format", passed: true, severity: "INFO"} } }
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.
- 2d ago First seen · 339 lines · 24 tokens per session scan A a067ba43b383
agent-validation-builder is an agent published in the GitHub repository yaleh/meta-cc (21 stars, last pushed 11d ago), licensed MIT. It adds 24 tokens to every session and 2,609 once invoked, about $0.0001 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
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.