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 slackgit 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/slack)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/slack"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/slack/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/slack"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/slack.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 | $0.00043 | $0.00300 |
| Opus 5.5 | $0.00017 | $0.00120 |
| Sonnet 5.5 | $0.00009 | $0.00060 |
| Haiku 4.5 | $0.00004 | $0.00030 |
Grade A, and why
slack 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 15d 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
Slack
Use the installed slack CLI. Start with slack status. If it reports
not_connected, run slack authorize-url and share only the returned
connect_url with the user.
Slack requires a fixed registered app identity and does not support Dynamic
Client Registration. The test app is limited to its development workspace;
the production app must be approved for Slack Marketplace distribution before
users from other workspaces can connect.
Run slack list-tools to inspect the reviewed subset of the live provider
catalogue and its permission annotations, then call an advertised tool with:
slack call-tool --name <tool> --arguments-json '<json-object>'
Slack's catalogue contains both reads and mutations and can change over time. The CLI allows only explicitly reviewed tools: read operations are allowed by default and mutations require approval with an argument preview. Unknown or new provider tools fail closed. Direct file reads, signed upload URLs, and unreviewed list tools remain unavailable until they have dedicated delivery handling. Never request OAuth tokens or app credentials in chat.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 15d ago First seen · 35 lines · 43 tokens per session scan A 669dd1c9af7f
slack is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (69,918 stars, last pushed today), licensed CC0-1.0. It adds 43 tokens to every session and 300 once invoked, about $0.0002 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 2026-10-05.
Other skills, from other repositories
things-mac
Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks OpenClaw to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
kanban-video-orchestrator
Plan and run multi-agent video production pipelines.
first-task
Run the first task chat that setup hands off.
initiate-setup
Run the first-run setup chat in the Hermes desktop app.
sdlc-review
Review Kanban handoffs and route verified outcomes.
himalaya
Himalaya CLI: IMAP/SMTP email from terminal.