Borrowing it
Nothing to install: this file belongs to Rethunk-AI/clodbridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Rethunk-AI/clodbridge/main/.cursor/skills/persist-context-to-memory/SKILL.mdgit 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/skills/rethunk-ai/clodbridge/persist-context-to-memory)<a href="https://agentmods.dev/skills/rethunk-ai/clodbridge/persist-context-to-memory"><img src="https://agentmods.dev/badge/skills/rethunk-ai/clodbridge/persist-context-to-memory/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/skills/rethunk-ai/clodbridge/persist-context-to-memory"><img src="https://agentmods.dev/badge/skills/rethunk-ai/clodbridge/persist-context-to-memory.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 | $0.00022 | $0.01545 |
| Opus 5 | $0.00011 | $0.00772 |
| Sonnet 5 | $0.00004 | $0.00309 |
| Haiku 4.5 | $0.00002 | $0.00154 |
Grade B, and why
persist-context-to-memory scanned grade B with 1 finding 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- MCP server registration: ~/.claude/settings.json mcpServers How it starts
The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persist Context to Memory
Why Memory Matters
Next session, you'll start fresh with no context about:
- How this user likes to work
- What decisions were made and why
- The project architecture
- Patterns that worked well
- Tools and references used
Memory bridges this gap. After a session, save what you learned so the next session picks up where you left off.
What to Save
User Memory
What you learned about how this user works:
---
name: User work preferences
description: How this user prefers to work, get feedback, and manage projects
type: user
---
- Prefers iterative feedback (commits, not code dumps)
- Values design validation before implementation
- Wants patterns documented in .cursor/rules/
- Escalates blockers rather than working around them
- Uses bun, not npm (due to sandbox issues)
Project Memory
Architectural decisions and structure:
---
name: clodbridge design
description: Core design, file formats, MCP exposure, technical stack
type: project
---
- Cursor files (.cursor/) are golden source
- Three concepts: Rules, Skills, Agents
- MCP exposes 6 tools, 6 resources, 1 prompt
- File watching via chokidar with 200ms debounce
- Tech stack: TypeScript, gray-matter, micromatch, zod
Feedback Memory
Guidance the user explicitly gave:
---
name: Development process feedback
description: Rules and patterns the user has validated
type: feedback
---
Rule: Commit early, commit often (< 8 files, < 500 LOC per commit)
Why: Small commits catch errors early and allow user feedback
How to apply: Commit after each logical unit, not in batches
Rule: Verify before proceeding
Why: Assumptions cause bugs; verification catches errors immediately
How to apply: npm run typecheck + npm test after each commit
Reference Memory
External resources and tools used:
---
name: Claude Code MCP integration
description: How Claude Code loads and uses MCP servers
type: reference
---
- MCP server registration: ~/.claude/settings.json mcpServers
- Hook events: SessionStart, PreToolUse, PostToolUse, UserPromptSubmit
- Cursor Rules format: .cursor/rules/*.mdc with YAML frontmatter
- References: docs.anthropic.com/claude-code/, Cursor docs, MCP spec
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.
- 8d ago First seen · 273 lines · 22 tokens per session scan B 5982cce9240a
persist-context-to-memory is a skill published in the GitHub repository Rethunk-AI/clodbridge (0 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 1,545 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
memorix-memory
Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.
memorix
Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.
memorix-mini-skills
Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.
memorix-git-memory
Use when the task depends on commit history, what changed, when a fix shipped, or linking engineering evidence to reasoning memory.
memorix-reasoning
Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.