identify-gaps-and-generate-epics

identify-gaps-and-generate-epics is a command for Claude Code from TheLobbi/claude. It costs 0 tokens per session (7,801 once invoked), scanned A, original, MIT.

A command that compares written requirements with what a codebase actually implements. It scans documentation and project files, finds missing or incomplete work, and turns the findings into planned development epics.

In plain words
What is it for?
Auditing documentation against implementation, identifying missing features, prioritizing gaps, and producing epics with dependencies and implementation plans.
Why use it?
It helps teams see where the software has drifted from its requirements and gives them organized work items to address the gaps.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Part of the claude-orchestration plugin — 6 skills, 133 commands, 9 agents, 8 hooks, 6 plugins shipped together

Good fit Auditing documentation against implementation, identifying missing features, prioritizing gaps, and producing epics with dependencies and implementation plans.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/thelobbi/claude/identify-gaps-and-generate-epics
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.

Clone the repo
git clone --depth 1 https://github.com/TheLobbi/claude

Made for: Claude Code.

Or install claude-orchestration, the plugin that ships this one along with the rest of its 6 skills, 133 commands, 9 agents, 8 hooks, 6 plugins.

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 identify-gaps-and-generate-epics

README.md
[![agentmods](https://agentmods.dev/badge/commands/thelobbi/claude/identify-gaps-and-generate-epics/github.svg)](https://agentmods.dev/commands/thelobbi/claude/identify-gaps-and-generate-epics)
Your own site
<a href="https://agentmods.dev/commands/thelobbi/claude/identify-gaps-and-generate-epics"><img src="https://agentmods.dev/badge/commands/thelobbi/claude/identify-gaps-and-generate-epics/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for identify-gaps-and-generate-epics

Your own site · 80×15
<a href="https://agentmods.dev/commands/thelobbi/claude/identify-gaps-and-generate-epics"><img src="https://agentmods.dev/badge/commands/thelobbi/claude/identify-gaps-and-generate-epics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,801 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.07801
Opus 5 $0.00000 $0.03900
Sonnet 5 $0.00000 $0.01560
Haiku 4.5 $0.00000 $0.00780

Measured 11d ago against content hash 16be15bb07c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

identify-gaps-and-generate-epics 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 11d 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/identify-gaps-and-generate-epics.md · 956 lines

How it starts

The opening of the file, as written. The whole thing — 956 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/identify-gaps-and-generate-epics

Scan documentation sources, analyze codebase implementation, identify gaps, and generate actionable epics with deep reasoning.


Purpose

This command orchestrates a comprehensive gap analysis workflow that:

  1. Discovers Requirements - Scans local documentation and Obsidian vault for requirements, specifications, and architectural decisions
  2. Analyzes Implementation - Inventories existing codebase features, patterns, and capabilities
  3. Identifies Gaps - Compares documented requirements against actual implementation to find missing features, incomplete implementations, and architectural drift
  4. Generates Epics - Uses sequential-thinking MCP to create detailed, prioritized epics with dependencies, user stories, and implementation strategies
  5. Produces Deliverables - Outputs gap analysis reports, priority matrices, and epic specifications ready for backlog integration

Best for: Organizations scaling development across multiple teams, ensuring alignment between requirements and implementation, and establishing sustainable backlog management practices.


Multi-Agent Coordination Strategy

This command uses the Blackboard Pattern for multi-agent coordination, where specialized agents contribute to a shared workspace:

graph TD
    BB[Blackboard<br/>Shared Workspace]

    %% Phase 1: Documentation Discovery
    R1[researcher-1<br/>Local Docs]
    R2[researcher-2<br/>Obsidian Vault]
    R3[researcher-3<br/>API Specs]

    %% Phase 2: Codebase Analysis
    REV[reviewer<br/>Feature Inventory]
    SA[system-architect<br/>Architecture State]
    BD[backend-dev<br/>Code Patterns]

    %% Phase 3: Gap Detection
    SEC[security-auditor<br/>Risk Assessment]
    REV2[reviewer<br/>Gap Categorization]
    SA2[system-architect<br/>Dependency Mapping]

    %% Phase 4: Epic Generation
    PO[product-owner<br/>Epic Synthesis]
    PLAN[planner<br/>Prioritization]
    DW[docs-writer<br/>Epic Documentation]
    SEQ[sequential-thinking<br/>MCP Reasoning]

    %% Phase 5: Output Generation
    DA[data-analyst<br/>Reports & Matrices]

    %% Connections
    R1 --> BB
    R2 --> BB
    R3 --> BB

    BB --> REV
    BB --> SA
    BB --> BD

    REV --> BB
    SA --> BB
    BD --> BB

    BB --> SEC
    BB --> REV2
    BB --> SA2

    SEC --> BB
    REV2 --> BB
    SA2 --> BB

    BB --> PO
    BB --> PLAN
    BB --> DW
    BB --> SEQ

    PO --> BB
    PLAN --> BB
    DW --> BB
    SEQ --> BB

    BB --> DA
    DA --> OUT[Epic Files<br/>Reports<br/>Matrices]

    style BB fill:#f9f,stroke:#333,stroke-width:4px
    style SEQ fill:#ff9,stroke:#333,stroke-width:2px
    style OUT fill:#9f9,stroke:#333,stroke-width:2px

Read the full file on GitHub · 956 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. 11d ago First seen · 956 lines · 0 tokens per session scan A 16be15bb07c6

Subscribe to this mod's changes

identify-gaps-and-generate-epics is a command published in the GitHub repository TheLobbi/claude (21 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,801 tokens. 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 2026-08-31.