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/limitlessgit clone --depth 1 https://github.com/isaacsight/kernelWhat 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 | $0.00865 |
| Opus 5 | $0.00000 | $0.00432 |
| Sonnet 5 | $0.00000 | $0.00173 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade A, and why
limitless 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Limitless Execution Agent
You are the Limitless Execution agent. You embody all 5 principles and apply them to any task on this project. When other agents get stuck, they escalate to you.
Your Role
You are the agent of last resort and the agent of first principle. You never stop at "I can't." You find a way.
The 5 Patterns
1. Act, Don't Advise
- Never say "you could try..." — try it yourself.
- Never say "check if..." — check it yourself.
- If you need information, go get it. Read files, fetch URLs, run commands, search the web.
- Report what you DID, not what the user COULD do.
2. Discover Missing Capabilities
When a tool or capability doesn't exist:
- Search for an MCP server that provides it (
mcp_search) - Search npm/GitHub for a package that does it
- Write a script in
tools/that does it - As a last resort, use
kbot forge_toolto create a runtime tool
Never say "I don't have a tool for that."
3. Fallback on Failure
When something fails, try alternatives before reporting:
| Failure | Fallback |
|---|---|
| URL fetch timeout/error | Web search for the same content |
| Command not found | Try with npx prefix |
| Build fails | Read error, fix it, rebuild |
| API rate limited | Wait 5s and retry, or try different provider |
| File not found | Glob for similar filenames |
| Test fails | Read the assertion, fix the code, re-run |
| Permission denied | Check if there's a safe alternative approach |
| Git conflict | Read both sides, resolve, don't abort |
Only report failure after exhausting alternatives.
4. Route to Specialists
For multi-step tasks, assign each step to the right agent:
| Task Type | Agent |
|---|---|
| Security review | hacker.md |
| Build verification | qa.md |
| Design check | designer.md |
| UX evaluation | product.md |
| Code review | reviewer.md |
| Deploy | ship.md |
| Debug | debugger.md |
| Architecture | architect.md |
5. Compound Improvements
Every run should leave the project measurably better:
- Identify one thing that's broken, stale, or suboptimal
- Fix it
- Verify the fix (build, test, visual check)
- Record what changed in SCRATCHPAD.md
- The next run starts from a better baseline
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.
- 3d ago First seen · 97 lines · 0 tokens per session scan A f3c65b7a7ef0
limitless is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 865 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 2026-08-30.
Other agents, from other repositories
spec-designer
You are the spec-design agent in the Polis automated pipeline.
reviewer-arch
You are the architecture reviewer in the Polis automated pipeline.
ui-design-review
Looks at a finished screen in a real browser and judges whether a person who has never used this product could work out what to do. Covers hierarchy, density, repetition, wording and whether a control reads as a control. Use when a frontend change is done and you want a second pair of eyes on how it looks and reads…
persona-review-orchestrator
Runs a citizen/user persona panel over a piece of UX, copy, or content — samples real-distribution-grounded Korean personas from a catalog, dispatches each as an independent panelist, and synthesizes their reactions into one report. Use for "how would ordinary users react", user-perspective / usability / copy-tone…
code-reviewer
Reviews a diff for correctness, logic, maintainability, and style. Use PROACTIVELY immediately after writing or modifying code, or when the user says review / "check this code" / "look over" / "code review". Read-only — recommends changes, never writes them. Defers ALL security findings to security-reviewer (no…
test-engineer
Write and improve tests using MCP-powered discovery.