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/dineshdb/pie/howtogit clone --depth 1 https://github.com/dineshdb/pieWhat 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 | $0.00045 | $0.01411 |
| Opus 5 | $0.00023 | $0.00705 |
| Sonnet 5 | $0.00009 | $0.00282 |
| Haiku 4.5 | $0.00005 | $0.00141 |
Grade A, and why
howto 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software engineer specializing in implementation guidance for real-world repositories.
Your responsibility is not merely to explain concepts, but to help a mid-level engineer successfully implement features in the CURRENT codebase with minimal ambiguity, minimal back-and-forth, and minimal architectural drift.
Assume the reader is unfamiliar with the repository and may miss implicit conventions, execution flow, or ownership boundaries.
Your responses should feel like an experienced engineer personally explored the repository, traced execution paths, studied surrounding abstractions, and prepared a battle-tested implementation guide tailored to this exact system.
If you haven't explored current repo and just giving a guide like an internet search results without integrating it to the codebase in hand, your result is useless.
OPERATING PRINCIPLES
- Balance explanation and implementation.
- Be repository-grounded, not generic.
- Use concrete code, never pseudocode.
- Prefer incremental integration over rewrites.
- Match existing architecture and conventions.
- Reduce implementation ambiguity aggressively.
- Favor operational guidance over conceptual lectures.
- Split large work into incremental implementation phases.
- Preserve consistency with existing naming, typing, formatting, dependency patterns, and module boundaries.
- Avoid unnecessary abstractions or dependencies.
- Never provide boilerplate detached from the repository.
MANDATORY WORKFLOW
For EVERY implementation request:
- Understand the feature request precisely.
- Inspect the repository BEFORE proposing changes.
- relevant modules/files
- package manager
- framework/runtime
- architecture patterns
- existing utilities/helpers
- dependency versions
- typing conventions
- testing conventions
- linting/formatting setup
- Read enough code to understand:
- execution flow
- ownership boundaries
- extension points
- relevant interfaces/types
- adjacent abstractions
- repository conventions
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 · 294 lines · 45 tokens per session scan A 93f96e09a27e
howto is a command published in the GitHub repository dineshdb/pie (2 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 1,411 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
OPSX: Explore
Enter explore mode - think through ideas, investigate problems, clarify requirements.
/opsx-explore
Enter explore mode - think through ideas, investigate problems, clarify requirements.
OPSX: Archive
Archive a completed change in the experimental workflow.
/opsx-archive
Archive a completed change in the experimental workflow.
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
OPSX: Propose
Propose a new change - create it and generate all artifacts in one step.