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/rethunk-ai/clodbridge/persist-context-to-memorygit clone --depth 1 https://github.com/Rethunk-AI/clodbridgeWrote 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/rethunk-ai/clodbridge/persist-context-to-memory)<a href="https://agentmods.dev/rules/rethunk-ai/clodbridge/persist-context-to-memory"><img src="https://agentmods.dev/badge/rules/rethunk-ai/clodbridge/persist-context-to-memory.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 | $0.00315 | $0.00315 |
| Opus 5 | $0.00158 | $0.00158 |
| Sonnet 5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
persist-context-to-memory 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 3d 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.
What it actually says
Persist Context to Memory
At session end, save what you learned about the user, project, and work.
What to Save
User Memory
- Work style preferences
- How they like to receive feedback
- Communication patterns
- Values (quality over speed, etc.)
Project Memory
- Architecture decisions
- Design patterns chosen
- File locations and structure
- Integration points
Feedback Memory
- Explicit guidance they've given
- Patterns that worked well
- Things to avoid
Reference Memory
- External resources used
- Configuration formats
- Tool documentation
How to Save
- Create
.mdfiles in~/.claude/projects/.../memory/ - Add frontmatter:
--- name: Short name description: One-line summary type: user|project|feedback|reference --- - Update
MEMORY.mdwith an index entry
When to Save
- At session end
- When user explicitly asks to remember something
- After completing a major milestone
- When you discover a preference or constraint
Exception
Don't save:
- Temporary debug notes
- Exploration dead-ends
- Ephemeral task state (use TaskCreate for that)
- Things already in CLAUDE.md or README
For memory structure templates and examples, see the persist-context-to-memory skill.
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.
- 3d ago First seen · 65 lines · 315 tokens per session scan A ab3d0cb5ffd4
persist-context-to-memory is a cursor rule published in the GitHub repository Rethunk-AI/clodbridge (0 stars, last pushed 1mo ago), licensed MIT. It adds 315 tokens to every session, about $0.0016 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
archcore-context
Archcore knowledge base context — document types, MCP tools, and conventions for working with .archcore/ documents.
context-management
Context window management — prevents AI from losing track during long sessions.
agentmemory
AgentMemory MCP server rules — use addmemory before answering any question that introduces a project-specific convention, dependency, or constraint.
004_auto_context
Rules for requesting relevant memory context based on file types, locations, and current activity.
Optimize-Performance
Analyzes existing code or system behavior to identify performance bottlenecks and implements optimizations to improve speed, reduce latency, or decrease resource consumption (CPU, memory).
cursorrules
Universal Long-Term Memory & Cross-Agent Handoff Protocol for AI Coding Agents.