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/aegntic/compound-engineering/deepen-plangit clone --depth 1 https://github.com/aegntic/compound-engineeringWhat 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 | $0.00029 | $0.07676 |
| Opus 5 | $0.00015 | $0.03838 |
| Sonnet 5 | $0.00006 | $0.01535 |
| Haiku 4.5 | $0.00003 | $0.00768 |
Grade B, and why
deepen-plan scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find .claude/docs -name "*.md" -type f 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 794 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deepen Plan - Power Enhancement Mode
Introduction
Note: The current year is 2026. Use this when searching for recent documentation and best practices.
This command takes an existing plan (from /workflows:plan) and, when available, the architecture improvement artifact from /workflows:architecture. If no artifact exists yet, it must assemble an explicit architecture handoff contract from the plan instead of treating architecture as hidden context. Every enhancement is grounded in the plan's WHY artifacts -- the problem narrative, user story, architectural context, success criteria, the explicit architecture contract, and the plan's TDD/evidence contract -- so that deepening adds purpose-aligned depth, not generic complexity.
Each major element gets its own dedicated research sub-agent to find:
- Best practices and industry patterns relevant to the user story
- Performance optimizations that matter for the stated success criteria
- UI/UX improvements (if applicable) aligned with the user's needs
- Quality enhancements and edge cases that could threaten success criteria
- Real-world implementation examples in similar architectural contexts
The result is a deeply grounded, production-ready plan that remains tightly coupled to WHY we're building it while honoring the deletion-test, interface, seam, and adapter decisions captured in the architecture artifact or explicit architecture handoff contract.
Plan File
<plan_path> #$ARGUMENTS </plan_path>
If the plan path above is empty:
- Check for recent plans:
ls -la docs/plans/ - Ask the user: "Which plan would you like to deepen? Please provide the path (e.g.,
docs/plans/2026-01-15-feat-my-feature-plan.md)."
Do not proceed until you have a valid plan file path.
Main Tasks
1. Parse and Analyze Plan Structure
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 · 794 lines · 29 tokens per session scan B 13481fb11da2
deepen-plan is a command published in the GitHub repository aegntic/compound-engineering (2 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 7,676 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
research
Professional equity research analysis with institutional-grade formatting.
cli-anything-web:list
List all available CLI-Anything-Web CLIs (installed and generated).
pi-code-review
Adversarial code review via Codex — break confidence in changes, not validate them.
review
Run a standard Gemini code review of recent git changes.
pi-ask-gemini
Ask Gemini a question — get Google's perspective alongside Claude's.
brd-reconcile
BRD reconciliation workflow (PM phase, sixth and last command of the BRD-to-PRD route). Takes the customer's returned review from anywhere, copies it into the BRD folder under the canonical name and commits it before anything reads it, then dispatches customer-review-reader in schema or free-text mode. Confirms every…