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/kangig94/coral/skill-qualitygit clone --depth 1 https://github.com/kangig94/coralWrote 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/kangig94/coral/skill-quality)<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>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 | $0.00027 | $0.01512 |
| Opus 5 | $0.00014 | $0.00756 |
| Sonnet 5 | $0.00005 | $0.00302 |
| Haiku 4.5 | $0.00003 | $0.00151 |
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 --> 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.
```
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.
- 5d ago First seen · 141 lines · 27 tokens per session scan C 98854621f0f1
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.
Other agents, from other repositories
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
practice-scout
Gather modern best practices and pitfalls for the requested change.
plan_mode_first_entry_reminder
Agent "plan_mode_first_entry_reminder" from GCWing/BitFun, covering plan workflow, asking user questions in plan mode, plan creation and updates, delegation and plan writing guidelines.
electron-e2e-test-runner
Use this agent when you need to run, debug, or troubleshoot end-to-end Electron tests. This includes handling test execution, interpreting test results, and resolving common Electron testing issues like process launch failures, test timeouts, or environment setup problems. Examples:\n\n \nContext: The user is working…
challenger
Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…
preflight
Pre-commit quality gate — catches 'almost right' code. Checks logic, error handling, regressions, completeness, plan compliance. BLOCK verdict stops commit.