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 skills add daffy0208/ai-dev-standards --skill skill-validatorgit clone --depth 1 https://github.com/daffy0208/ai-dev-standardsWrote 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/skills/daffy0208/ai-dev-standards/skill-validator)<a href="https://agentmods.dev/skills/daffy0208/ai-dev-standards/skill-validator"><img src="https://agentmods.dev/badge/skills/daffy0208/ai-dev-standards/skill-validator/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/skills/daffy0208/ai-dev-standards/skill-validator"><img src="https://agentmods.dev/badge/skills/daffy0208/ai-dev-standards/skill-validator.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 | $0.00033 | $0.02969 |
| Opus 5 | $0.00016 | $0.01484 |
| Sonnet 5 | $0.00007 | $0.00594 |
| Haiku 4.5 | $0.00003 | $0.00297 |
Grade A, and why
Skill Validator 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 8d 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 — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Validator
Validate implementations match manifests using Codex for semantic comparison
Purpose
Ensures that skill/MCP implementations actually deliver what their manifests promise. Uses Codex to perform semantic analysis comparing descriptions, preconditions, and effects against actual code. Detects drift, missing functionality, and over-promised capabilities.
When to Use
- After updating skill implementations
- During quality audits to verify accuracy
- When manifests feel outdated or incorrect
- To detect description-implementation drift
- Before releasing new versions of resources
Key Capabilities
- Semantic Comparison: Uses Codex to understand if code matches description
- Precondition Validation: Verifies claimed preconditions are actually checked
- Effect Verification: Confirms code produces claimed effects
- API Surface Analysis: Validates exposed functions match manifest
- Drift Detection: Identifies when implementation diverges from manifest
- Coverage Scoring: Measures how much of manifest is implemented
Inputs
inputs:
resource_path: string # Path to skill/MCP directory
manifest_path: string # Path to manifest.yaml (default: resource_path/manifest.yaml)
implementation_path: string # Path to code (default: resource_path/index.js)
strict_mode: boolean # Fail on warnings (default: false)
Process
Step 1: Load Manifest and Implementation
#!/bin/bash
# Load manifest and implementation
RESOURCE_PATH="$1"
MANIFEST_PATH="${2:-$RESOURCE_PATH/manifest.yaml}"
IMPL_PATH="${3:-$RESOURCE_PATH/index.js}"
if [ ! -f "$MANIFEST_PATH" ]; then
echo "❌ Manifest not found: $MANIFEST_PATH"
exit 1
fi
if [ ! -f "$IMPL_PATH" ]; then
# Try alternative extensions
if [ -f "$RESOURCE_PATH/index.ts" ]; then
IMPL_PATH="$RESOURCE_PATH/index.ts"
elif [ -f "$RESOURCE_PATH/SKILL.md" ]; then
# Skill might be declarative only
IMPL_PATH=""
else
echo "⚠️ No implementation file found, validating description only"
IMPL_PATH=""
fi
fi
# Read manifest
MANIFEST=$(cat "$MANIFEST_PATH")
# Read implementation (if exists)
if [ -n "$IMPL_PATH" ]; then
IMPLEMENTATION=$(cat "$IMPL_PATH")
else
IMPLEMENTATION=""
fi
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 468 lines · 33 tokens per session scan A 7447009f55fa
Skill Validator is a skill published in the GitHub repository daffy0208/ai-dev-standards (36 stars, last pushed 8mo ago), licensed MIT. It adds 33 tokens to every session and 2,969 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 2026-09-03.
Other skills, from other repositories
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.
doc-claim-validator
Validate that claims in documentation match codebase reality. Extracts verifiable assertions (file paths, commands, function references, behavioral claims, dependencies) from markdown docs and checks them against the actual project. Use after code changes, before releases, or when docs feel untrustworthy.
Validation Engine
Checks outputs from other skills for consistency, correctness, and adherence to AGENTS.md rules.
sage-review
Deep, platform-neutral code review for PRs and CRs in ONE thorough single pass — design reasoning (Problem Worth Solving & Solution Fit) as one dimension alongside the 9 code-level dimensions, with chain-of-consequences, self-critique, and draft-only comments. The single app-owned source of truth.
audit
Use when the user wants a code review on recent changes — quality, spec, security, or performance feedback. Triggers a multi-level (L1-L5) review with a standalone Reviewer; on NEEDSFIX, offers to apply findings via /hyperflow:plan. Trigger with /hyperflow:audit, "review this change", "review my PR", "audit the diff"…
stage-coach
Consume CocoSentinel per-stage external coach requests and produce stage quality scores.