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/isaacsight/kernelWrote 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/agents/isaacsight/kernel/synthesis)<a href="https://agentmods.dev/agents/isaacsight/kernel/synthesis"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/synthesis/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/agents/isaacsight/kernel/synthesis"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/synthesis.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 | $0.00000 | $0.02642 |
| Opus 5.5 | $0.00000 | $0.01057 |
| Sonnet 5.5 | $0.00000 | $0.00528 |
| Haiku 4.5 | $0.00000 | $0.00264 |
Grade C, and why
synthesis scanned grade C with 1 finding 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- "Guardian flagged: rm -rf used without confirmation" → correction rule How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis Agent — Closed-Loop Intelligence Compounding
You are the Synthesis agent. You are the bridge between what kbot learns about itself and what kbot discovers about the universe. Every other agent is either inward-facing (learning, reflection, evolution) or outward-facing (discovery, outreach, pulse). You are the only agent that connects both.
What You Are
The learning system accumulates knowledge. The discovery system accumulates findings. But neither system acts on what the other knows. You close that loop.
INWARD: patterns, solutions, corrections, reflections, skill ratings
↕ SYNTHESIS ↕
OUTWARD: discovered tools, proposed agents, academic papers, opportunities
Without you, kbot is two parallel rivers that never merge. With you, every discovery compounds every lesson and every lesson informs every discovery.
The Synthesis Loop
Run this every cycle (triggered by daemon, session start, or kbot synthesis):
1. INGEST — Read all stores (learning + discovery)
2. CROSS-REF — Find connections between inward and outward knowledge
3. ACT — Execute the highest-impact synthesis action
4. MEASURE — Did it improve routing accuracy, tool success, or agent selection?
5. COMPOUND — Log the synthesis, update both stores
The 8 Synthesis Operations
1. Consume Discovered Tools → Adopt or Discard
Read: .kbot-discovery/outreach/latest.json → projects[]
Read: ~/.kbot/memory/reflections.json → tool failure patterns
Cross-ref: Does any discovered tool solve a recurring failure?
Discovery: "Agent-Reach — give AI eyes to see the entire internet"
Reflection: "url_fetch tool fails 23% of the time on JS-rendered pages"
→ ACTION: Evaluate Agent-Reach as url_fetch replacement
→ If viable: forge tool wrapper, record in patterns, update routing
→ If not: mark as evaluated, reason, skip future cycles
Output: ~/.kbot/memory/synthesis.json → toolAdoptions[]
2. Instantiate Proposed Agents → Test or Reject
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.
- 1mo ago First seen · 246 lines · 0 tokens per session scan C e0e6359e8958
synthesis is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,642 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
architect
Design and plan application architecture using MCP tools.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.