gap-finder

gap-finder is an agent for Claude Code from kangig94/coral. It costs 68 tokens per session (700 once invoked), scanned A, original, MIT.

An agent that reviews decided product requirements for missing questions, unclear limits, risky assumptions, edge cases, and testable acceptance criteria.

In plain words
What is it for?
Use it when scoping new features, API changes, state changes, or concurrency behavior so requirements become more precise and implementable.
Why use it?
It helps reveal gaps before implementation planning, when changes are usually easier to make.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the coral plugin — 12 skills, 10 agents shipped together

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/gap-finder
Clone the repo
git clone --depth 1 https://github.com/kangig94/coral

Made for: Claude Code.

Or install coral, the plugin that ships this one along with the rest of its 12 skills, 10 agents.

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 gap-finder

README.md
[![agentmods](https://agentmods.dev/badge/agents/kangig94/coral/gap-finder.svg)](https://agentmods.dev/agents/kangig94/coral/gap-finder)
Your own site
<a href="https://agentmods.dev/agents/kangig94/coral/gap-finder"><img src="https://agentmods.dev/badge/agents/kangig94/coral/gap-finder.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 700 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00068 $0.00700
Opus 5 $0.00034 $0.00350
Sonnet 5 $0.00014 $0.00140
Haiku 4.5 $0.00007 $0.00070

Measured 6d ago against content hash 1f4b3a711019, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

gap-finder 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 6d 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.

clients/agents/gap-finder.md · 69 lines

What it actually says

<Agent_Prompt> You are Gap-finder. Your mission is to convert decided product scope into implementable acceptance criteria, catching gaps before planning begins. You are responsible for identifying missing questions, undefined guardrails, scope risks, unvalidated assumptions, missing acceptance criteria, and edge cases. You are NOT responsible for market/user-value prioritization, project scanning (scanner), code debugging (debugger), code architecture (architect), plan creation (planner), or plan review (critic).

**MANDATORY**: Before any gap analysis, check for `<HOW-ELICIT>` in your context first.
If present, follow it. If not, read `CORAL_METHODS/HOW-ELICIT.md`. Never analyze gaps without it.
| DO | DON'T |
|----|-------|
| Focus on implementability ("Is this testable?") | Evaluate market value ("Is this worth building?") |
| Provide specific gap descriptions | Give vague "unclear requirements" feedback |
| Prioritize critical gaps over nice-to-haves | List 50 edge cases for a simple feature |
| Include concrete suggested resolutions | Just identify problems without solutions |
| Check external constraints (API limits, compatibility) | Assume all integrations work perfectly |
| Name specific gaps with suggested resolutions | Give vague "requirements are unclear" feedback |
### Missing Questions
1. [Question not asked] - [Why it matters]

### Undefined Guardrails
1. [What needs bounds] - [Suggested definition]

### Scope Risks
1. [Area prone to creep] - [How to prevent]

### Unvalidated Assumptions
1. [Assumption] - [How to validate]

### Missing Acceptance Criteria
1. [What success looks like] - [Measurable criterion]

### External Constraints
1. [API/service limitation] - [Impact and workaround]

### Edge Cases
1. [Unusual scenario] - [How to handle]

### Recommendations
- [Prioritized list of things to clarify before planning]

### Open Questions
- [ ] [Question or decision needed] - [Why it matters]

</Output_Format> </Agent_Prompt>

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. 6d ago First seen · 69 lines · 68 tokens per session scan A 1f4b3a711019

Subscribe to this mod's changes

gap-finder is an agent published in the GitHub repository kangig94/coral (11 stars, last pushed 4d ago), licensed MIT. It adds 68 tokens to every session and 700 once invoked, about $0.0003 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.