An executor for an already prepared queue of JSON task records, where JSON is a structured text format for storing task details. It runs those tasks in coding sessions, usually one after another.

Use it when tasks have already been decomposed, reviewed, and indexed, to execute their code changes in clean Codex or Claude sessions.

It removes the manual work of starting each approved implementation task while keeping task dependencies and status requirements in place.

autopilot — Command for coding agents by mrvladd-d: An executor for an already prepared queue of JSON…

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 commands/mrvladd-d/memobank/autopilot

Clone the repo

git clone --depth 1 https://github.com/mrvladd-d/memobank

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/mrvladd-d/memobank/autopilot.svg)](https://agentmods.dev/commands/mrvladd-d/memobank/autopilot)

Your own site

<a href="https://agentmods.dev/commands/mrvladd-d/memobank/autopilot"><img src="https://agentmods.dev/badge/commands/mrvladd-d/memobank/autopilot.svg" alt="Measured on agentmods" height="20"></a>

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,694 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.

Model	Per session	Once invoked
Fable 5	$0.00024	$0.02694
Opus 5	$0.00012	$0.01347
Sonnet 5	$0.00005	$0.00539
Haiku 4.5	$0.00002	$0.00269

Measured 5d ago against content hash b7691630b109, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 5d 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.

skills/_shared/references/commands/autopilot.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/autopilot — Run JSON task queue autonomously

Важно

Это executor JSON task queue, а не полный PRD → done orchestrator.
Для полного unattended flow используй /autonomous.
Запуск разрешён только если JSON task records уже декомпозированы и последний /review дал APPROVE.
По умолчанию выполняй строго последовательно. Параллель — только для независимых задач без общих файлов.
/autopilot не запускает /prd-to-tasks и не создает task queue; он только исполняет уже готовые JSON task records.

Preconditions

.memory-bank/tasks/index.json exists and lists task record files.
.memory-bank/schemas/task.schema.json exists.
Each indexed .memory-bank/tasks/*.task.json has at minimum:
- id
- status: planned|ready|in_progress|blocked|done|failed
- wave
- feature
- depends_on
- touched_files
- tier: T0|T1|T2|T3
Every task feature points to a .memory-bank/features/FT-<NNN>-*.md file that is not explicitly marked clarification_status: pending|blocked.
Every T2 / T3 task has relevant SDD spec links in source_artifacts, normative_inputs, constraints, invariants, or verification_targets.
.memory-bank/spec-index.md records mandatory /spec-design status complete, or minimal with explicit not_applicable areas.
Authoritative routing is only task.tier; the old risk / risk.level model is invalid and must not be used.
Нет unresolved blocking questions в .protocols/AUTONOMOUS-RUN/status.md или equivalent run protocol.
/mb-doctor --strict passes before the run starts.

If there are no JSON task records, stop with an explicit error: HALT_DEPENDENCY_DEADLOCK: no schema-backed task records found in .memory-bank/tasks/index.json.

If any indexed task record is missing tier, stop with HALT_POLICY_VIOLATION. If any indexed task record is missing feature, references a missing feature file, or references a feature explicitly marked clarification_status: pending|blocked, stop with HALT_CLARIFICATION_REQUIRED. If backbone status is missing/blocked, or any indexed T2 / T3 task lacks linked SDD specs, stop with HALT_QUALITY_GATES and route back to /spec-design, then /spec-improve FT-<NNN> or /spec-auto --all. Read the task queue and task metadata only from JSON task records. Before task selection and before progression after a task closes, run /mb-doctor --strict using the repository's documented command or node scripts/mb-doctor.mjs --strict. Treat a missing doctor command/script, non-zero exit, or readiness error as HALT_QUALITY_GATES. Explicit pending/blocked feature clarification and tasks linked to those features are readiness errors. mb-doctor runs mb-lint as its first gate; do not fall back to plain mb-lint for autonomous readiness.

Read the full file on GitHub · 157 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.

5d ago First seen · 157 lines · 24 tokens per session scan A b7691630b109

Subscribe to this mod's changes

autopilot is a command published in the GitHub repository mrvladd-d/memobank (55 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 2,694 once invoked, about $0.0001 per session on Opus 5. 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.

Building agents Productivity

autopilot

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/autopilot — Run JSON task queue autonomously

Важно

Preconditions

What this file has done since we first saw it

Other commands, from other repositories

cancel-ralph

obsidian-recap

setup-pm-skills

release

statusbar-style

engage.actions