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.
git clone --depth 1 https://github.com/TheLobbi/claudeWrote 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/commands/thelobbi/claude/identify-gaps-and-generate-epics)<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.
<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>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 5.1 | $0.00000 | $0.07801 |
| Opus 5 | $0.00000 | $0.03900 |
| Sonnet 5 | $0.00000 | $0.01560 |
| Haiku 4.5 | $0.00000 | $0.00780 |
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.
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:
- Discovers Requirements - Scans local documentation and Obsidian vault for requirements, specifications, and architectural decisions
- Analyzes Implementation - Inventories existing codebase features, patterns, and capabilities
- Identifies Gaps - Compares documented requirements against actual implementation to find missing features, incomplete implementations, and architectural drift
- Generates Epics - Uses sequential-thinking MCP to create detailed, prioritized epics with dependencies, user stories, and implementation strategies
- 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
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.
- 11d ago First seen · 956 lines · 0 tokens per session scan A 16be15bb07c6
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.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.