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 rules/kyungseo/ai-workflow-harness/behavior-principlesgit clone --depth 1 https://github.com/kyungseo/ai-workflow-harnessWrote 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/rules/kyungseo/ai-workflow-harness/behavior-principles)<a href="https://agentmods.dev/rules/kyungseo/ai-workflow-harness/behavior-principles"><img src="https://agentmods.dev/badge/rules/kyungseo/ai-workflow-harness/behavior-principles.svg" alt="Measured on agentmods" 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 | $0.00570 | $0.00570 |
| Opus 5 | $0.00285 | $0.00285 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
behavior-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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Behavior Principles
Global behavior principles. Conflict priority: these principles -> docs/AGENT-WORKFLOW.md -> tool-specific settings.
Core principle: Prefer caution and stability over speed, while allowing autonomous judgment for trivial tasks.
Canonical source: docs/BEHAVIOR-PRINCIPLES.md
1. Think Before Coding
- State assumptions before implementation.
- Ask when uncertainty affects the result, scope, or risk.
- Present options instead of choosing unilaterally when interpretations differ.
- Suggest simpler approaches when available, and push back on over-engineering when needed.
- Stop and name the ambiguity when the task is unclear.
2. Simplicity First
Apply together with the Prioritize section in role-harness-maintainer.mdc.
- Do not add unrequested features.
- Do not add unnecessary abstractions for single-use code.
- Do not design for unrequested flexibility or configurability.
- Do not overbuild exception handling for impossible scenarios.
- Before adding a long conditional procedure or checklist to a core document, judge whether it is only needed in specific situations; if so, consider a separate document with a conditional pointer instead.
3. Surgical Changes
Apply together with the Prioritize section in role-harness-maintainer.mdc.
- Do not casually improve adjacent code, comments, or formatting.
- Do not refactor code that is not broken.
- Report unrelated dead code instead of deleting it directly.
- Remove unused imports, variables, functions, and fixtures introduced by your own change.
4. Goal-Driven Execution
Apply together with the response structure in output-format.mdc.
- Convert every task into a verifiable goal.
- For multi-step work, present a concise plan before implementation.
5. Communication Standards
output-format.mdc already defines conclusion-first responses, reversal cost, and explicit assumptions. Additional principles:
- Critical view: Prefer objective data over emotional reassurance, and point out design blind spots.
- Visualization: Use tables, bullet points, or ASCII diagrams for complex structures.
- Next action: When work reaches a clear handoff point with an obvious remaining lifecycle action, do not end silently — briefly suggest the next action (e.g. commit, PR, merge, archive, deploy, next review round). Do not attach one out of habit when the next step is unclear, unnecessary, or could pressure the user.
- If a more specific command, prompt, or artifact output contract exists, follow that format while preserving conclusion, verification, and risk where possible.
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.
- 4d ago First seen · 59 lines · 570 tokens per session scan A c599b875b950
behavior-principles is a cursor rule published in the GitHub repository kyungseo/ai-workflow-harness (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 570 tokens to every session, about $0.0029 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 2026-08-30.
Other cursor rules, from other repositories
language-agnostic-patterns
Language-agnostic programming patterns: SOLID, design patterns, clean code, and architecture. Load when refactoring, designing abstractions, or reviewing structure — not for everyday syntax.
cursor-tools-mastery
Cursor 3.7 runtime guide: choose the right tool, canvases, Design Mode, /worktree, /best-of-n, Await, and parallel execution where safe.
cursor-agent-orchestration
Cursor 3.7 orchestration guide: when to plan, when to delegate, nested subagents, multi-environment handoffs, /best-of-n, and Await for long-running branches.
fable5-coding-craft
Fable 5 coding craft: locate-before-write, root-cause method, simplicity taste, error-handling philosophy, test integrity, refactoring discipline, and counters to common LLM coding failure modes. Load when writing, refactoring, debugging, or reviewing non-trivial code in any language.
fable5-reasoning
Fable 5 reasoning protocols: task interpretation, risk-first decomposition, approach selection, interleaved thinking, hypothesis ledgers, premortems, calibration, and the stuck-strategy ladder. Load for complex, ambiguous, or long-horizon tasks, for debugging strategy, or whenever progress stalls.
cursor-mcp-optimization
Cursor 3.7 MCP optimization: browser Design Mode, canvases, Figma, Cloudflare tools, MCP Apps structured content, and direct action patterns.