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.
git clone --depth 1 https://github.com/ctxpipe-ai/ctxpipeWrote 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/ctxpipe-ai/ctxpipe/ai-memory)<a href="https://agentmods.dev/rules/ctxpipe-ai/ctxpipe/ai-memory"><img src="https://agentmods.dev/badge/rules/ctxpipe-ai/ctxpipe/ai-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/rules/ctxpipe-ai/ctxpipe/ai-memory"><img src="https://agentmods.dev/badge/rules/ctxpipe-ai/ctxpipe/ai-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 | $0.00657 | $0.00657 |
| Opus 5.5 | $0.00263 | $0.00263 |
| Sonnet 5.5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
ai-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 21d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local memory (.ai/memory)
Read order (non-trivial tasks)
- .ai/memory/README.md
- .ai/memory/index.md
- .ai/memory/lessons-learned.md when conventions matter
- .ai/memory/decisions/index.md — then one ADR if needed
- .ai/memory/product-context.md selectively
Do not load every ADR or the entire memory tree by default.
Recall (unknown fact)
- Start at
.ai/memory/index.md(then a storeindex.mdif the category is clear). - Otherwise search with ripgrep, excluding the candidate inbox:
rg -i "keyword" .ai/memory --glob '*.md' --glob '!events/**'
- Open one matching file/section. Use the
memory-searchskill for the full procedure. - No AgentMemory / embeddings process — Markdown + indexes +
rgonly.
Write / promote
- Host hooks only append candidates under
.ai/memory/events/(gitignored). - Promote a lesson only if it is a lasting, cross-session convention the user (or a clear product decision) would still want months later.
- Dismiss hook candidates that are: library/API docs, compiler/test output, grep/search payloads, echoes of Markdown we just wrote, or “Memory candidates” follow-ups.
- Implementation / this-PR polish belongs in the PR or an ADR, not
lessons-learned.md. - Hook follow-ups are not user product requests; if they fail the bar, dismiss ids and end the turn — do not start a research turn.
- Promote durable knowledge with capture skills (
capture-adr,capture-lesson,capture-glossary,capture-decision). - Always update the relevant
index.mdwhen adding or renaming durable entries. - Never commit secrets into
.ai/memory/.
Commit and share
- Memory is shared with teammates (and the ctx| graph) only once it merges. Include
.ai/memory/changes in the commit for the work they came from, on that work's branch — not a separate memory branch. - Summarize the work in the pull request description: what changed, why, what was tried and ruled out, follow-ups. Use
sessions/only for work with no PR. - Describe people by role, not by name or email address.
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.
- 21d ago Changed · +6 lines · +105 tokens per session a7f75c46c268
- 1mo ago First seen · 46 lines · 552 tokens per session scan A c1ca2cb2de42
ai-memory is a cursor rule published in the GitHub repository ctxpipe-ai/ctxpipe (26 stars, last pushed today), licensed MIT. It adds 657 tokens to every session, about $0.0026 per session on Opus 5.5. 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
ult-institutional-memory-distill
Distill decisions, reasoning, and rejected alternatives from PRs, design docs, and postmortems into the project's decisionledger, so ult-context-generate's trip-wire can surface institutional memory before new work quietly repeats settled ground. Do NOT use to query the ledger against new work or decide…
demo-consume-context
Worked example that discovers, loads, and tags a context package per CONSUMING-CONTEXT-PACKAGE.md, then writes a reverse-index addendum — proves the produce/consume/tag loop end-to-end. Do NOT use for real feature work.
aictx
Cursor rule "aictx" from oldskultxo/aictx, covering aictx, priority model, default loop, inspection and advanced tools and what to record.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.