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 commands/thelobbi/claude/implement-epicgit clone --depth 1 https://github.com/TheLobbi/claudeWhat 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 | $0.00000 | $0.03075 |
| Opus 5 | $0.00000 | $0.01537 |
| Sonnet 5 | $0.00000 | $0.00615 |
| Haiku 4.5 | $0.00000 | $0.00308 |
Grade A, and why
implement-epic 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.
How it starts
The opening of the file, as written. The whole thing — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/implement-epic
Execute an entire epic with full orchestration, dependency management, quality gates, and real-time progress tracking.
Usage
```bash /implement-epic [--dry-run] [--resume-from=checkpoint-id] ```
Parameters
epic-id(required): Epic identifier (e.g.,epic-2-net-orchestration)--dry-run(optional): Preview execution plan without running tasks--resume-from(optional): Resume from specific checkpoint after failure
What This Command Does
This command orchestrates the complete execution of an epic using the workflow-orchestrator agent with the following capabilities:
1. Planning Phase
- Load epic definition from workflow DSL (YAML/JSON)
- Build dependency graph (DAG) and calculate critical path
- Assign agents to tasks based on capabilities
- Estimate timeline with P10/P50/P90 projections
- Validate pre-epic quality gates
2. Execution Phase
- Execute tasks according to workflow pattern (Sequential/Parallel/Saga)
- Coordinate multi-agent communication via SignalR
- Manage distributed state with Cosmos DB + event sourcing
- Enforce quality gates at task, phase, and epic levels
- Handle retries with exponential backoff
- Create automatic checkpoints for recovery
3. Monitoring Phase
- Real-time progress dashboard showing:
- Current phase and task status
- Agent utilization and workloads
- Blocked tasks waiting on dependencies
- ETA based on actual vs estimated time
- Critical path delays
- OpenTelemetry distributed tracing
- Prometheus metrics (task duration, success rate, agent utilization)
4. Quality Assurance Phase
- Post-task quality gates:
senior-reviewer: Code quality assessmentsecurity-specialist: Security vulnerability scantest-engineer: Test coverage validation (≥85%)performance-optimizer: Performance benchmarks (P95 <500ms)
- Blocking vs non-blocking gates configurable per task
- Automatic rollback on blocking failure (if Saga pattern)
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.
- 2d ago First seen · 360 lines · 0 tokens per session scan A 808df31142d7
implement-epic is a command published in the GitHub repository TheLobbi/claude (21 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,075 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.