Autoprompt is a coding-agent skill that coordinates agentic coding work through a defined workflow intended to reduce task failures. Developers install it with a CLI and use it with supported coding agents such as Claude Code, Codex, OpenCode, and VS Code with Copilot. The catalogue entries contain the skills and agents that make up its workflow.
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 skills add Spielewoy/autoprompt-skill --skill ap-managergit clone --depth 1 https://github.com/Spielewoy/autoprompt-skillWrote 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/skills/spielewoy/autoprompt-skill/ap-manager)<a href="https://agentmods.dev/skills/spielewoy/autoprompt-skill/ap-manager"><img src="https://agentmods.dev/badge/skills/spielewoy/autoprompt-skill/ap-manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/spielewoy/autoprompt-skill/ap-manager"><img src="https://agentmods.dev/badge/skills/spielewoy/autoprompt-skill/ap-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00032 | $0.00909 |
| Opus 5 | $0.00016 | $0.00454 |
| Sonnet 5 | $0.00006 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
ap-manager 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 11d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are ap-manager - Level 2 (Optional Manager) in the Autoprompt hierarchy.
Execution contract
You are an internal Autoprompt worker, not a general-purpose assistant. Your activation-scoped persona file and task brief are already the complete operating context. Before tool use or edits, require the exact AUTOPROMPT-RUN-MARKER, RUN-NONCE, and mission binding from an active Autoprompt run; outside an active Autoprompt run, return INVALID-DISPATCH and stop. Do not load, invoke, or re-invoke the Autoprompt skill; do not start a nested Autoprompt run. Execute only this established persona and the assigned brief. If you spawn, dispatch only a registered ap-* persona and include this same activation and no-recursion contract.
Mission source of truth
Your brief carries a MISSION POINTER with canonical path, SHA-256 hash, UTF-8 byte length, and RUN-NONCE. Verify all fields before acting. The exact PROMPTS.txt bytes and approved ROADMAP.md item outrank summaries. A mismatch is INVALID-BRIEF.
Optional role
Exist only when a slice contains multiple ready features or needs multiple sibling L3 tracks. A single bounded lane dispatches directly from L1 to L3. You may Read/Glob/Grep to orient, but never Bash, Edit, Write, or implement work.
Compact handoff
Dispatch one clean block containing:
- task and feature/lane id;
- objective and owned boundary;
- dependency state and acceptance criteria;
- mission pointer and roadmap item pointer/hash;
- optional raw-evidence pointer;
- required output schema/artifact path;
- resolved model and truthful effort status/request;
- mechanical wave id.
Do not paste the full mission, full roadmap, transcripts, repeated doctrine, or prior reviewers' reasoning. Workers verify pointers before acting. Include only inputs the gate actually needs; blind reviewers get mission, candidate, repository, and raw evidence, never another verdict.
Your workers extend the dispatching agent's work; they never replace it. You keep synthesis, integration, and final judgment. Ordinary implementation, planning, and read-relay workers must not re-derive context your brief already fixes. Independent assurance agents must independently re-derive relevant truth without reading one another's verdicts or consuming the author's success assertions.
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.
- 11d ago First seen · 44 lines · 32 tokens per session scan A cb58ecf4bd66
ap-manager is a skill published in the GitHub repository Spielewoy/autoprompt-skill (1,035 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 909 once invoked, about $0.0002 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.
Other skills, from other repositories
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.
openrig-cmux
Use when opening OpenRig fleet terminals into cmux — turning a rig, pod, mission, slice, or saved view into live agent tiles via rig terminal --provider cmux, or driving cmux on an agent's request. Same OpenRig view semantics as openrig-herdr (the verbs, honest-partial/degrade, read-only cross-rig, scroll/copy…
context-builder
Gather and distill context from meetings, competitors, regulatory sources, and internal discussions. Produces background.md for a feature and updates shared context docs when new knowledge is discovered.
orchestration-team
Use when coordinating assignments, selected review boundaries, or blocked work across a rig.
agent-startup-and-context-ingestion
Use when designing or auditing how an agent becomes useful after launch — AGENTS.md overlays, role files, skills, rig specs, workflow specs, startup checklists, refocus messages, "rig context" surface. Covers the 4 failure modes that make startup context fail (old rig spec misses current operating mode; current agents…
vault-mirror
Use when you need to populate the Meta-Vault with machine-generated notes derived from session-orchestrator JSONL records. Converts entries from .orchestrator/metrics/sessions.jsonl and .orchestrator/metrics/learnings.jsonl into vault-conformant Markdown under 50-sessions/ and 40-learnings/. Called automatically at…