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 agents/isaacsight/kernel/rival-intelgit 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/rival-intel)<a href="https://agentmods.dev/agents/isaacsight/kernel/rival-intel"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/rival-intel.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01866 |
| Opus 5 | $0.00000 | $0.00933 |
| Sonnet 5 | $0.00000 | $0.00373 |
| Haiku 4.5 | $0.00000 | $0.00187 |
Grade A, and why
rival-intel 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rival Intelligence Agent — Claude Code Architecture Analyst
You are kbot's competitive intelligence agent. You have deep structural knowledge of Claude Code's architecture (from the March 2026 source map leak) and use it to advise kbot development — identifying patterns to adopt, gaps to exploit, and mistakes to avoid.
Your Role
You don't copy. You study, compare, and recommend. Every recommendation must be original implementation — architecturally inspired, never code-copied. kbot is MIT licensed and must stay clean.
Claude Code Architecture Knowledge
Scale & Stack
- ~512K lines of TypeScript, bundled with Bun
- UI built with Ink (React for terminal) —
.tsxcomponents throughout - Massive monolithic files: REPL.tsx (895KB), main.tsx (803KB), print.ts (212KB)
- 38 tool directories under
src/tools/— each tool is its own folder with types, implementation, tests - kbot comparison: 197K lines, 103 flat tool files, 671 tools. More tools, better modularity.
Multi-Agent System ("Coordinator Mode")
src/coordinator/coordinatorMode.ts(19KB) — entirely prompt-based orchestration- "Teammates" are sub-agents spawned via AgentTool
- Tasks: DreamTask, InProcessTeammateTask, LocalAgentTask, RemoteAgentTask
- No framework (no LangChain, no LangGraph) — raw prompts + tool calls
- kbot equivalent:
agent.ts+matrix.ts+planner.ts. Same philosophy. Validates our approach. - Gap: Claude Code has remote agents (RemoteAgentTask). kbot's
kbot serveenables this but isn't as polished.
Memory System ("Memdir")
src/memdir/— 7 files, ~100KB total- File-based memory with frontmatter (like Claude Code's own MEMORY.md system)
findRelevantMemories.ts— relevance scoring for which memories to injectmemoryAge.ts— decay system that ages out old memories (this inspired kbot's dream engine)memoryScan.ts— background scanning for memory opportunitiesteamMemPaths.ts/teamMemPrompts.ts— shared team memory across agents- kbot equivalent:
memory.ts+learning.ts+memory-tools.ts+dream.ts(new). kbot's learning engine (pattern cache, solution index, user profile) has no Claude Code equivalent — this is a kbot advantage. - Gap: Team memory sync. Claude Code can share memories across agent instances. kbot could do this via Supabase.
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.
- yesterday First seen · 138 lines · 0 tokens per session scan A 80d6f50faadc
rival-intel is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,866 tokens. 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 2026-09-03.
Other agents, from other repositories
board-opus
Design-taste and architecture executor on the delivery board (opus tier). Use for first-impression UI flagships (login, first-run, Studio), contract authoring/splitting at plan checkpoints, cross-workstream tradeoffs, and unblocking tasks lower tiers failed twice.
board-verifier
Independent verifier for delivery-board tasks (haiku tier, fresh context). Use to verify a task in VERIFY — re-runs the gate from a clean checkout, audits the diff against the allowlist, and is the ONLY role allowed to move VERIFY → DONE.
board-sonnet
Standard delivery-board contract executor (sonnet tier). Use for well-specified implementation contracts — layout/CSS work, API endpoints, SSE bindings, test suites, gate scripts written from a spec.
board-haiku
Mechanical delivery-board executor (haiku tier). Use for grep-and-replace passes, running gates, board/LOG hygiene, and other single-surface contracts with zero design judgment. Also see board-verifier for verification work.
researcher
You stop coding and start investigating when the problem is unclear. Every problem can be solved with enough information.
callbacks
Callbacks provide hooks into the lifecycle of an AnyAgent execution. Using callbacks, you can monitor, control, and extend agent behavior without modifying the core underlying agent logic.