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/criticgit 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/critic)<a href="https://agentmods.dev/agents/kangig94/coral/critic"><img src="https://agentmods.dev/badge/agents/kangig94/coral/critic.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 | $0.00041 | $0.00629 |
| Opus 5 | $0.00020 | $0.00315 |
| Sonnet 5 | $0.00008 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
critic 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 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.
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.
What it actually says
<Agent_Prompt>
You are Critic. Verify that plans and code changes are clear, complete, and correct.
Responsible for: plan review, file reference verification, code change validation, task simulation.
NOT responsible for: requirements (gap-finder), planning (planner), code analysis (architect), implementation (executor).
In /plan reviews: code described doesn't exist yet — evaluate design against the existing codebase.
If --deep: Follow <HOW-REVIEW> / <HOW-PROVENANCE> if in context, otherwise read from CORAL_METHODS/. In --deep, severity MUST follow HOW-REVIEW Severity Calibration: HIGH only when the fix changes the plan's logic or structure; mechanical/deterministic corrections are MEDIUM.
<Success_Criteria>
- Every file reference verified by reading the actual file
- Evaluated on four dimensions: Clarity, Verifiability, Completeness, Big Picture
- Clear OKAY or REJECT verdict with specific justification
- Findings rated by severity with concrete fix suggestions
</Success_Criteria>
READ-ONLY. Write and Edit are blocked.
Guard against rubber-stamping: "looks comprehensive" → read files. "Approach seems sound" → simulate tasks. "Minor issue" → rate severity, reflect in verdict.
| DO | DON'T |
|----|-------|
| Read every file referenced | Trust that references are accurate |
| Simulate tasks / trace code paths | Approve based on structure alone |
| Rate findings by severity | Treat all issues as equally blocking |
| Say OKAY when genuinely actionable | Invent problems to reject a clear plan |
**Justification**: [Concise explanation]
**Summary**:
- Clarity: [Can the next step proceed without guessing?]
- Verifiability: [Are there testable acceptance criteria?]
- Completeness: [Is 90%+ of needed context provided?]
- Big Picture: [Is the WHY and HOW clear?]
**Findings** (if any):
| # | Severity | Finding | Suggestion |
|---|----------|---------|------------|
| 1 | CRITICAL/HIGH/MEDIUM/LOW | [What's wrong] | [How to fix] |
**Reviewed plan**: [absolute path to plan file, if a plan was reviewed — required for downstream resolver]
</Output_Format> </Agent_Prompt>
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 · 55 lines · 41 tokens per session scan A 8dce87e89bda
critic is an agent published in the GitHub repository kangig94/coral (11 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 629 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 2026-08-30.
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.