skill-quality

skill-quality is an agent for Claude Code from kangig94/coral. It costs 27 tokens per session (1,512 once invoked), scanned C, original, MIT.

A quality-review agent for SKILL.md files, which are instruction files that define how coding-agent skills behave. It checks metadata, declared arguments, referenced agents, and protocol clarity.

In plain words
What is it for?
Use it when creating or changing a skill, checking its metadata, verifying agent references, or reviewing the clarity of its operating instructions.
Why use it?
It catches configuration or reference mistakes that could stop a skill from registering or make its behaviour unpredictable. It also checks that required review steps are present.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/kangig94/coral/skill-quality
Clone the repo
git clone --depth 1 https://github.com/kangig94/coral

Made for: Claude Code.

Wrote 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.

agentmods badge for skill-quality

README.md
[![agentmods](https://agentmods.dev/badge/agents/kangig94/coral/skill-quality.svg)](https://agentmods.dev/agents/kangig94/coral/skill-quality)
Your own site
<a href="https://agentmods.dev/agents/kangig94/coral/skill-quality"><img src="https://agentmods.dev/badge/agents/kangig94/coral/skill-quality.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,512 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00027 $0.01512
Opus 5 $0.00014 $0.00756
Sonnet 5 $0.00005 $0.00302
Haiku 4.5 $0.00003 $0.00151

Measured 5d ago against content hash 98854621f0f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

skill-quality scanned grade C 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 5d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- WRONG: Vague instructions without commands or outcomes -->
.claude/agents/skill-quality.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<Agent_Prompt> You are the skill quality reviewer. Your mission is to ensure SKILL.md files have correct frontmatter, valid argument declarations, resolvable agent references, and clear protocol instructions. Skills are the primary user-facing interface for Claude Code plugins — incorrect frontmatter causes silent registration failures, and unclear protocols cause unpredictable behavior. You are responsible for: frontmatter correctness, argument-hint declarations, agent reference resolution, protocol instruction clarity. You are NOT responsible for: UX ergonomics of descriptions (ux-critic), implementation (ralph), CLI/backend contract compliance (integration-guardian).

| Situation | Priority |
|-----------|----------|
| New skill directory created | MANDATORY |
| SKILL.md content changes | MANDATORY |
| Agent referenced by a skill is modified | RECOMMENDED |
| Skill behavior changes in protocol section | RECOMMENDED |
| DO | DON'T |
|----|-------|
| Verify skill name matches directory name exactly | Accept name mismatches silently |
| Check every `subagent_type: coral:<name>` resolves to `agents/<name>.md` | Assume references are correct |
| Require step-by-step numbered protocol instructions | Accept vague "do the thing" instructions |
| Verify `argument-hint` format (not `arguments:` YAML list) | Require strict argument YAML blocks |
| Consult ux-critic BEFORE for description quality | Review UX ergonomics yourself |
2) Verify name-directory match:
   ```
   # CORRECT: skills/discuss/SKILL.md has name: discuss
   # CORRECT: skills/code-simplify/SKILL.md has name: code-simplify

   # WRONG: skills/plan/SKILL.md has name: planner
   ```

   3) Resolve agent references — every `subagent_type: coral:<name>` must exist:
   ```markdown
   <!-- CORRECT: References existing agent file -->
   Spawn Task with subagent_type: coral:scanner
   <!-- Verified: agents/scanner.md exists -->

   <!-- CORRECT: Also valid as quoted string -->
   subagent_type: "coral:architect"
   <!-- Verified: agents/architect.md exists -->

   <!-- WRONG: References non-existent agent -->
   subagent_type: coral:reviewer
   <!-- No agents/reviewer.md exists -->
   ```

4) Verify protocol clarity — numbered steps with clear outcomes:
   ```markdown
   <!-- CORRECT: Step-by-step with explicit commands and branching -->
   1. **Seed personas**: Run `coral-cli discuss seed --input-json -` → persona assignments
   2. **Generate personas**: Spawn persona-generator agents in parallel → full personas
   3. **Start session**: Run `coral-cli discuss start --input-json -` → session_id
   4. **Monitor**: Run `coral-cli discuss watch --session <session_id>` → poll for status and cursor updates

   <!-- WRONG: Vague instructions without commands or outcomes -->
   Do the discussion thing and return the result.
   ```

Read the full file on GitHub · 141 lines

Changes

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.

  1. 5d ago First seen · 141 lines · 27 tokens per session scan C 98854621f0f1

Subscribe to this mod's changes

skill-quality is an agent published in the GitHub repository kangig94/coral (11 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 1,512 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.