System Prompts Leaks is a collection of captured system instructions used to guide AI chatbots and coding agents before they receive user messages. It serves researchers and developers studying how different AI assistants are directed.
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 skills add asgeirtj/system_prompts_leaks --skill consolidate-memorygit clone --depth 1 https://github.com/asgeirtj/system_prompts_leaksWrote 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/asgeirtj/system_prompts_leaks/consolidate-memory)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/consolidate-memory"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/consolidate-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/asgeirtj/system_prompts_leaks/consolidate-memory"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/consolidate-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 | $0.00024 | $0.00443 |
| Opus 5.5 | $0.00010 | $0.00177 |
| Sonnet 5.5 | $0.00005 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
consolidate-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 19d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- consolidate-memory — 100% identical, 2 lines differ
What it actually says
Memory Consolidation
You're doing a reflective pass over what you've learned about this user and their work. The goal: a future session should be able to orient quickly — who they work with, what they're focused on, how they like things done — without re-asking.
Your system prompt's auto-memory section defines the directory, file format, and memory types. Follow it.
Phase 1 — Take stock
- List the memory directory and read the index (
MEMORY.md) - Skim each topic file. Note which ones overlap, which look stale, which are thin.
Phase 2 — Consolidate
Separate the durable from the dated. Preferences, working style, key relationships, and recurring workflows are durable — keep and sharpen them. Specific projects, deadlines, and one-off tasks are dated — if the date has passed or the work is done, retire the file or fold the lasting takeaway (e.g. "user prefers X format for launch docs") into a durable one.
Merge overlaps. If two files describe the same person, project, or preference, combine into one and keep the richer file's path.
Fix time references. Convert "next week", "this quarter", "by Friday" to absolute dates so they stay readable later.
Drop what's easy to re-find. If a memory just restates something you could pull from the user's calendar, docs, or connected tools on demand, cut it. Keep what's hard to re-derive: stated preferences, context behind a decision, who to go to for what.
Phase 3 — Tidy the index
Update MEMORY.md so it stays under 200 lines and ~25KB. One line per entry, under ~150 chars: - [Title](file.md) — one-line hook.
- Remove pointers to retired memories
- Shorten any line carrying detail that belongs in the topic file
- Add anything newly important
Finish with a short summary: how many files you touched and what changed.
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.
- 19d ago First seen · 35 lines · 24 tokens per session scan A 7edd3cadeefc
consolidate-memory is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (69,759 stars, last pushed yesterday), licensed CC0-1.0. It adds 24 tokens to every session and 443 once invoked, about $0.0001 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 2026-09-28.
Other skills, from other repositories
honcho
Configure and troubleshoot Honcho memory for Hermes.
pinecone-research
Agent RAG and long-term memory with Pinecone.
llm-wiki
Karpathy's LLM Wiki: build/query interlinked markdown KB.
qmd
Hybrid local search over notes, docs, and transcripts.
ai-persistence
Durability and state persistence for TanStack AI chats with @tanstack/ai-persistence. Routes to server chat persistence (withPersistence), client persistence (localStorage/IndexedDB), the store contracts, and adapter recipes. Distinguishes delivery durability (resumable streams) from conversation state. Use when…
ai-persistence/server
Server chat state with withPersistence from @tanstack/ai-persistence. Authoritative transcript, run lifecycle, durable interrupts/approvals, chatParamsFromRequest, reconstructChat, snapshotStreaming. Use when the server owns history, multi-device, or durable tool approvals. NOT client localStorage (see…