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/assafkip/kipi-systemWrote 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/plugins/assafkip/kipi-system/kipi-core)<a href="https://agentmods.dev/plugins/assafkip/kipi-system/kipi-core"><img src="https://agentmods.dev/badge/plugins/assafkip/kipi-system/kipi-core/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/plugins/assafkip/kipi-system/kipi-core"><img src="https://agentmods.dev/badge/plugins/assafkip/kipi-system/kipi-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
kipi-core 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 8d 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
{
"name": "kipi-core",
"version": "1.13.48",
"description": "Core founder OS \u2014 voice, research, AUDHD, LinkedIn/brand, RCA skills + kipi-mcp server",
"author": {
"name": "Assaf Kipnis",
"email": "[REDACTED]"
},
"repository": "https://github.com/assafkip/kipi-system",
"license": "MIT",
"skills": "./skills/",
"mcpServers": "./.mcp.json"
}
What it installs
The manifest is a name and a version. 10 skills, 9 commands travel with it, and installing the plugin installs all of them — 818 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill audhd-executive-function A 23 tokens
- Skill learn-from-correction A 45 tokens
- Skill research-mode A 35 tokens
- Skill deck-ai A 57 tokens
- Skill improve A 98 tokens
- Skill linkedin-brand A 35 tokens
- Skill founder-voice A 22 tokens
- Skill headline-engineering A 122 tokens
- Skill architecture-review A 105 tokens
- Skill rca A 100 tokens
- Command wiring-check A 37 tokens
- Command design-chain A 0 tokens
- Command linear-drain A 13 tokens
- Command say A 16 tokens
- Command rca-start A 15 tokens
- Command rca-check A 13 tokens
- Command voice-loop A 23 tokens
- Command voice-refresh A 59 tokens
- Command q-research A 0 tokens
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.
- 8d ago Changed abc422984305
- 10d ago Changed 9642398e352a
- 11d ago Changed 254d1a4a3dda
- 12d ago Changed d91abec02eb4
- 15d ago Changed e9a4a5aae1c5
- 16d ago Changed 3c2b035492fb
- 18d ago Changed 127c2a36a14a
- 19d ago Changed 98b668f19411
- 21d ago Changed 29aef0f5077f
- 22d ago First seen · 14 lines scan A c9ecd65dec8d
kipi-core is a plugin published in the GitHub repository assafkip/kipi-system (121 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
mnemonic
Pure filesystem-based memory system for Claude Code with custom ontology support.
hipocampus
Persistent agent memory that survives across sessions — auto-compacting 3-tier memory with hybrid search. Your agent remembers what it learned, decided, and built.
context-canopy
Portable personal AI context: search and capture knowledge, then read allowlisted user authority across agents.
trove
Repository memory for Claude Code: index symbols and architecture, progressively retrieve context beyond the context window, and capture durable engineering decisions in a personal trove.
remember
Extended Second Brain that learns as you work in Claude Code.
ConsiderateCoder
Development methodology plugin: Clean Architecture x TDD x three-tier delegation (communicator / orchestrator / worker) with /plan-sdd, /outsource, /dig and /refactor commands.