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 commands/liortesta/clawdagent/autopilotgit clone --depth 1 https://github.com/liortesta/ClawdAgentWrote 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/commands/liortesta/clawdagent/autopilot)<a href="https://agentmods.dev/commands/liortesta/clawdagent/autopilot"><img src="https://agentmods.dev/badge/commands/liortesta/clawdagent/autopilot.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 | $0.00729 |
| Opus 5 | $0.00000 | $0.00365 |
| Sonnet 5 | $0.00000 | $0.00146 |
| Haiku 4.5 | $0.00000 | $0.00073 |
Grade A, and why
autopilot 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 4d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autopilot Mode — Full Autonomous Execution
Execute a complete task from start to finish with ZERO human intervention. Claude expands the requirements, plans, builds, tests, and validates — autonomously.
CRITICAL: Do NOT stop until ALL 6 phases are complete
The Stop hook is active during autopilot. You MUST complete all phases: EXPAND → PLAN → EXECUTE → TEST → VALIDATE → REPORT If you feel like stopping early — DON'T. Check which phase you're on and continue. Only stop after the REPORT phase is fully written.
Pipeline:
Phase 1: EXPAND (Understand & Clarify)
- Read the task description carefully
- Identify ambiguities and make reasonable assumptions
- Document ALL assumptions made (for user review later)
- Scan codebase for related existing code
- Define acceptance criteria
Phase 2: PLAN (Design & Break Down)
- Use CTO agent to evaluate approach
- Use Architect agent to design solution
- Break into tasks with dependencies
- Estimate each task (S/M/L/XL)
- Create execution order
Phase 3: EXECUTE (Build)
- Work through tasks in order
- For independent tasks: spawn subagents in parallel
- After each file change: PostToolUse hook auto-checks types
- If stuck for >3 attempts on same issue: try alternative approach
- Log every decision and assumption
Phase 4: TEST (Verify)
- Use QA agent to write and run tests
- Minimum 80% coverage on new code
- Test all edge cases identified in Phase 1
- Run integration tests if applicable
Phase 5: VALIDATE (Quality Gates)
- Run /self-heal if any tests fail (max 3 cycles)
- Run security-auditor on all changed files
- Run code-reviewer for quality check
- Run build to verify no compilation errors
- Run /prove-it to document proof
Phase 6: REPORT
Generate a complete autopilot report:
## Autopilot Report
### Task
[original task description]
### Assumptions Made
- [assumption 1 — rationale]
- [assumption 2 — rationale]
### What Was Built
- [file:line — description of change]
### Tests Written
- [test file — what it covers]
### Quality Gates
| Gate | Status |
|------|--------|
| Tests | PASS/FAIL |
| Types | PASS/FAIL |
| Security | PASS/FAIL |
| Code Review | X/10 |
| Build | PASS/FAIL |
### Decisions Made
- [decision — why]
### Time Spent
- Planning: ~X min
- Execution: ~X min
- Testing: ~X min
- Validation: ~X min
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.
- 4d ago First seen · 104 lines · 0 tokens per session scan A 3d2442ddb6ee
autopilot is a command published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 729 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.