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/major7apps/pensyve/memory-informed-refactorgit clone --depth 1 https://github.com/major7apps/pensyveWhat 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 | $0.00018 | $0.00599 |
| Opus 5 | $0.00009 | $0.00300 |
| Sonnet 5 | $0.00004 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
memory-informed-refactor 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 60 lines · 18 tokens per session scan A b2856a3dd25a
memory-informed-refactor is a cursor rule published in the GitHub repository major7apps/pensyve (72 stars, last pushed 4d ago), with no licence file. It adds 18 tokens to every session and 599 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 2026-08-30.
Other cursor rules, from other repositories
debug-capture-pipeline
Debug llm-wiki-memory capture/recall — flush breadcrumbs, daily-vs-compile lag, failed-distill stash recovery, embedding cache, hook wiring. Use when memory didn't capture, doesn't recall, or a hook/cron looks broken.
self-observability
Self-observability (watch llm-wiki-memory while you work; offer fixes) — This rule applies to every AI agent (Claude Code, Cursor, Codex, generic MCP clients) working Canonical file is .agents/rules/self-observability.md.
triage-review-findings
Skill: triage review findings without acting on false positives — Full criteria for the guard-deletion case below: .agents/rules/defensive-invariants.md. Canonical file is .agents/skills/triage-review-findings.md.
docs-style
README and docs style for llm-wiki-memory — install-first structure, plain-English jargon, vertical Mermaid with quoted labels, badge rules. Canonical file is .agents/rules/docs-style.md.
verification-completeness
Verification completeness — What "verified" and "green" are allowed to mean in this repo. Canonical file is .agents/rules/verification-completeness.md.
format
Teach your coding agent — Claude Code, Cursor, or any AGENTS.md agent — your project's conventions, and turn every correction into a team-shared, git-tracked lesson.