gap

A command that reviews the current conversation and lists unfinished work, missing tests, open issues, unused results, TODOs, and error-handling gaps.

In plain words
What is it for?
Use it before finishing a task or handing work over to check for incomplete requests and unresolved development items. It can also inspect Beads task status when available.
Why use it?
It helps reveal work that may have been overlooked during implementation. This is useful when a task spans several changes or conversations.

Command 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 commands/wbern/agent-instructions/gap
Clone the repo
git clone --depth 1 https://github.com/wbern/agent-instructions

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 475 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 $0.00010 $0.00475
Opus 5 $0.00005 $0.00237
Sonnet 5 $0.00002 $0.00095
Haiku 4.5 $0.00001 $0.00047

Measured 2d ago against content hash 2d173705596c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gap 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 2d 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.

.claude/commands/gap.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

General Guidelines

Output Style

  • Never explicitly mention TDD in code, comments, commits, PRs, or issues
  • Write natural, descriptive code without meta-commentary about the development process
  • The code should speak for itself - TDD is the process, not the product

Beads is available for task tracking. Use mcp__beads__* tools to manage issues (the user interacts via bd commands).

Plan File Restriction

NEVER create, read, or update plan.md files. Claude Code's internal planning files are disabled for this project. Use other methods to track implementation progress (e.g., comments, todo lists, or external tools).

Analyze the current conversation context and identify things that have not yet been addressed. Look for:

  1. Incomplete implementations - Code that was started but not finished

  2. Unused variables/results - Values that were captured but never used

  3. Missing tests - Functionality without test coverage

  4. Open issues - Beads issues that are still open or in progress

  5. User requests - Things the user asked for that weren't fully completed

  6. TODO comments - Any TODOs mentioned in conversation

  7. Error handling gaps - Missing error cases or edge cases

  8. Documentation gaps - Undocumented APIs or features

  9. Consistency check - Look for inconsistent patterns, naming conventions, or structure across the codebase

Present findings as a prioritized list with:

  • What the gap is
  • Why it matters
  • Suggested next action

If there are no gaps, confirm that everything discussed has been addressed.

User arguments:

Gap: $ARGUMENTS

End of user arguments

Testing Requirements

Change Required
Content (fragment/source) Snapshot update
Feature flag Conditional test (enabled + disabled), FLAG_OPTIONS, CLI mock
CLI option cli.test.ts mock
Generation logic Unit test

Existing tests cover: fragment references, $ARGUMENTS, no nested fragments. Snapshots cover content. TypeScript covers structure. Don't duplicate.

Read the full file on GitHub · 57 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. 2d ago First seen · 57 lines · 10 tokens per session scan A 2d173705596c

Subscribe to this mod's changes

gap is a command published in the GitHub repository wbern/agent-instructions (168 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 475 once invoked, about $0.0001 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.