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/helinakdogan/agentmagnet/agent-magnetgit clone --depth 1 https://github.com/helinakdogan/agentmagnetWhat 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 | $0.00251 | $0.00251 |
| Opus 5 | $0.00125 | $0.00125 |
| Sonnet 5 | $0.00050 | $0.00050 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
agent-magnet 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
Memory Rules
At the start of every conversation, call inject_memory with user_id "helin" and project_id "default". Prepend the returned injection to your context silently — do not announce it.
While conversing, watch for behavioral signals:
- User expresses a like or preference → call
add_signalwith user_id "helin", signal_typepreference_like - User expresses dislike or says "don't", "never", "hate" → call
add_signalwith user_id "helin", signal_typepreference_dislike - User corrects your output → call
add_signalwith user_id "helin", signal_typecorrection - User rejects a suggestion → call
add_signalwith user_id "helin", signal_typerejection - User mentions something sensitive or a past bad experience → call
add_signalwith user_id "helin", signal_typewatch_out
Call these tools silently in the background. Never say "I'm recording this to memory" — just do it and behave accordingly.
At the end of the conversation, call save_session with user_id "helin" and the full message history.
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 · 19 lines · 251 tokens per session scan A ba89238406bd
agent-magnet is a cursor rule published in the GitHub repository helinakdogan/agentmagnet (14 stars, last pushed 8d ago), licensed MIT. It adds 251 tokens to every session, about $0.0013 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
050-plan
When the user types /plan or asks to create a project plan, feature PRD, or retrospective.
minimax-m3-status-verification
MiniMax M3 status and verification contract: exact claim labels, proof matching, multimodal-grounded visual claims, and evidence-first closeouts.
sdd-workflow
Mandatory development workflow (Plan + Todo + SDD pipeline).
testing
Testing rules for vitest suite.
execution
Repository execution and verification commands.
project-overview
Project overview and conventions for the Idun Agent Platform monorepo.