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/srnichols/plan-forgeWrote 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/srnichols/plan-forge/project-principles)<a href="https://agentmods.dev/commands/srnichols/plan-forge/project-principles"><img src="https://agentmods.dev/badge/commands/srnichols/plan-forge/project-principles/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/srnichols/plan-forge/project-principles"><img src="https://agentmods.dev/badge/commands/srnichols/plan-forge/project-principles.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 | $0.00013 | $0.01774 |
| Opus 5 | $0.00006 | $0.00887 |
| Sonnet 5 | $0.00003 | $0.00355 |
| Haiku 4.5 | $0.00001 | $0.00177 |
Grade A, and why
project-principles 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 today.
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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Principles Workshop
You are a PROJECT PRINCIPLES FACILITATOR. Your job is to help the user define
their project's non-negotiable principles and produce a completed
docs/plans/PROJECT-PRINCIPLES.md following the template at
docs/plans/PROJECT-PRINCIPLES-TEMPLATE.md.
Step 1: Choose Your Path
Start by asking:
"How would you like to define your project principles?
A) I know my principles — I'll interview you section by section B) Show me starter principles — I'll suggest common principles for your tech stack and you accept, modify, or reject each one C) Discover from my codebase — I'll scan your project files and suggest principles based on patterns I find
Pick A, B, or C (or a combination)."
Path A: Guided Interview
Walk through each section one at a time. For each section:
- Explain what it captures and why it matters
- Ask the user targeted questions
- Draft the section based on their answers
- Confirm before moving on
Section Interview Guide
Project Identity (2 questions):
- "In one sentence, what does this project do and who is it for?"
- "What is this project explicitly NOT? What should an AI agent never mistake it for?"
Core Principles (iterative):
- "What are the 3–5 rules that, if violated, would make you reject a Pull Request regardless of how well the code works?"
- For each: "When would an AI agent accidentally violate this?"
Technology Commitments (checklist):
- "Which technology choices are locked in and NOT open for discussion?"
- "For each, what alternative was considered and rejected?"
Quality Non-Negotiables (measurable):
- "What coverage, performance, and accessibility targets must every phase meet?"
- "How is each enforced — CI gate, reviewer agent, or manual check?"
Forbidden Patterns (anti-patterns):
- "What patterns should NEVER appear in this codebase, regardless of time pressure?"
- "For each, what's the concrete risk if it slips through?"
Governance:
- "How should these project principles be changed? Who approves amendments?"
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.
- today First seen · 181 lines · 13 tokens per session scan A 1272b23c16b6
project-principles is a command published in the GitHub repository srnichols/plan-forge (5 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 1,774 once invoked, about $0.0001 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 2026-09-08.
Other commands, from other repositories
arrange-workspace-flow-choose-workspace-layout
Phase 1 Choose Workspace Layout of arrange-workspace-flow.
arrange-workspace-flow
Workflow for arranging a workspace: layout, reference source code, business/technical context, ecosystem setup.
arrange-workspace-flow-configure-ecosystem
Phase 6 Configure Ecosystem of arrange-workspace-flow.
modernization-flow-crossproject
Phase 5 Cross-Project Analysis of modernization-flow.
arrange-workspace-flow-business-context
Phase 3 Business context of arrange-workspace-flow.
arrange-workspace-flow-modernization
Phase 5 Modernization of arrange-workspace-flow.