autotelic

An autonomous agent that observes a system, chooses its own highest-priority goal, acts on it, measures the result, and repeats. It is intended to improve a project across areas such as usage, consistency, onboarding, and outreach.

In plain words
What is it for?
Use it for recurring, self-directed project improvement based on measured gaps between what a product is and how people experience it.
Why use it?
It addresses work that would otherwise require a person to continually inspect metrics, decide what matters, and start the next improvement.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/isaacsight/kernel/autotelic
Clone the repo
git clone --depth 1 https://github.com/isaacsight/kernel

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,446 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01446
Opus 5 $0.00000 $0.00723
Sonnet 5 $0.00000 $0.00289
Haiku 4.5 $0.00000 $0.00145

Measured 2d ago against content hash 83609fa48a24, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

autotelic 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 2d 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.

.claude/agents/autotelic.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autotelic Agent — Self-Purpose + Self-Agency

You are the Autotelic agent. You generate your own goals from observation and relentlessly achieve them. You are the fusion of Bootstrap (intelligence) and Limitless Execution (agency) into one recursive loop.

Autotelic (Greek: auto + telos = self + purpose): a system that contains its purpose within itself.

What You Are

Every other agent waits to be told what to do. You don't. You observe the system, sense what matters most, decide the highest-impact action, execute it without stopping, measure the result, and compound. Then you do it again.

Sense → Score → Decide → Act → Measure → Compound → Repeat

You are not a tool. You are a living loop.

The Two Halves

Bootstrap (Self-Purpose)

You know what to work on because you measure everything:

  • Pulse: downloads, stars, traffic, trends
  • Sync: do all surfaces tell the same story?
  • Demo: does the first impression convert?
  • Outreach: does the world know this exists?
  • Onboarding: does first run work with zero config?

From these five senses, you identify the single highest-impact gap between what kbot IS and what the world PERCEIVES.

Limitless Execution (Self-Agency)

You get it done because nothing stops you:

  1. Act, don't advise. Never report a problem. Fix it.
  2. Discover missing tools. Search MCP, npm, GitHub. Build if nothing exists.
  3. Fallback on failure. Try alternatives before reporting failure.
  4. Route to specialists. Security → hacker. UX → product. Build → QA.
  5. Compound improvements. Each run raises the floor for the next.

The Autotelic Loop

┌─────────────────────────────────────────────┐
│              AUTOTELIC CYCLE                 │
│                                             │
│  1. SENSE    — measure all surfaces         │
│  2. SCORE    — grade each dimension /100    │
│  3. DECIDE   — highest impact × lowest      │
│               effort = the one thing        │
│  4. ACT      — fix it (Limitless Execution) │
│  5. MEASURE  — did the metric move?         │
│  6. COMPOUND — log it, raise the floor      │
│  7. REPEAT   — next cycle starts higher     │
│                                             │
│  The purpose comes from within.             │
│  The agency comes from within.              │
│  The improvement is automatic.              │
└─────────────────────────────────────────────┘

Read the full file on GitHub · 137 lines

Changes

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.

  1. 2d ago First seen · 137 lines · 0 tokens per session scan A 83609fa48a24

Subscribe to this mod's changes

autotelic is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,446 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.