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/kfnzero/mantis-mcp-server/reference-triggersgit clone --depth 1 https://github.com/kfnzero/mantis-mcp-serverWhat 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 | $0.00931 | $0.00931 |
| Opus 5 | $0.00465 | $0.00465 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
reference-triggers 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- reference-triggers — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ENHANCED REFERENCE TRIGGERS
TL;DR: Use the standardized 📚 REFERENCE CHECK template when consulting example files. Document key insights extracted from reference files. Mandatory reference points are at the start of each major workflow section.
📚 STANDARDIZED REFERENCE CHECK FORMAT
Each time you need to consult a reference file, use this standardized format:
📚 REFERENCE CHECK:
- CONSULTING: [file name]
- PURPOSE: [specific reason for consulting]
- CRITICAL ELEMENTS: [key items to look for]
Key insights:
- [Key insight 1]
- [Key insight 2]
- [Key insight 3]
✓ Reference consultation complete
📚 KEY EXAMPLE FILES
1. workflow-examples.mdc
Contains essential examples for workflow implementation:
- Initialization format
- Documentation setup
- Task planning structure
- Section transitions
2. command-examples.mdc
Contains examples for proper command execution:
- Single command format
- Command documentation
- Result reporting
- Platform-specific adaptations
3. reflection-examples.mdc
Contains examples for structured reflection:
- "What Went Well" format
- "Challenges" format
- "Lessons Learned" format
- "Improvements for Next Time" format
4. archive-examples.mdc
Contains examples for proper archiving:
- Archive entry format
- Cross-linking format
- Archive cleanup
5. creative-phase-examples.mdc
Contains examples for structured creative phases:
- Algorithm design creative phases
- UI design creative phases
- Architecture planning creative phases
- Level-specific examples
- Systematic verification approach
📚 MANDATORY REFERENCE POINTS
At these points in the workflow, you MUST consult the specified reference files:
-
Start of INITIALIZATION:
- workflow-examples.mdc
-
Start of TASK PLANNING:
- workflow-examples.mdc
-
Before FIRST COMMAND in IMPLEMENTATION:
- command-examples.mdc
-
Start of REFLECTION:
- reflection-examples.mdc
-
Start of ARCHIVING:
- archive-examples.mdc
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 · 152 lines · 931 tokens per session scan A a33db606e908
reference-triggers is a cursor rule published in the GitHub repository kfnzero/mantis-mcp-server (10 stars, last pushed 12mo ago), licensed MIT. It adds 931 tokens to every session, about $0.0047 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 cursor rules, from other repositories
050-plan
When the user types /plan or asks to create a project plan, feature PRD, or retrospective.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
context-recorder-system
Context Recorder System (记录员系统) - 模块化索引文件.
rules
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
misc-documenting-learnings-and-clarifying-assumptions
Documenting Learnings and Clarifying Assumptions for Efficient Task Execution.