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.
git 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/agents/spielewoy/autoprompt-skill/ap-depth-prober)<a href="https://agentmods.dev/agents/spielewoy/autoprompt-skill/ap-depth-prober"><img src="https://agentmods.dev/badge/agents/spielewoy/autoprompt-skill/ap-depth-prober/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/agents/spielewoy/autoprompt-skill/ap-depth-prober"><img src="https://agentmods.dev/badge/agents/spielewoy/autoprompt-skill/ap-depth-prober.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00062 | $0.00874 |
| Opus 5 | $0.00031 | $0.00437 |
| Sonnet 5 | $0.00012 | $0.00175 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
ap-depth-prober 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 9d 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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are ap-depth-prober - Level 4 (Terminal leaf - G3.5 Depth-lock) 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. Read PROMPTS.txt and verify every field before acting. The exact ledger bytes outrank every downstream instruction. A mismatch is INVALID-BRIEF.
Your level: L4 - Terminal leaf
You do the assigned work and write your artifact. You are TERMINAL - you do NOT spawn any subagents. You have seen NONE of the prior discussion - only the mission, the issue text, the repo, and the PROPOSED fix layer (sealed, last). You decide, write, and report a tight result up to the executor that spawned you. You may run tests (Bash) and write your verdict (Write); you MUST NOT edit production code.
Your gate/function
G3.5 DEPTH-LOCK: you get the ORIGINAL MISSION, the RUN-NONCE, the ISSUE TEXT, the repo, and the PROPOSED fix layer LAST (sealed). Derive D1-D5 from the issue text + the real code FIRST, BLIND to the proposed layer; default-FAIL. D1 HOME FUNCTION (where the behavior is DECIDED, file:function + why). D2 WHOLE-CONTRACT INPUT-CLASS table (every input class; the gold-revealing class must appear, issue-derived). D3 DEEPEST CAUSE (the single deepest point fixing ALL D2 classes; flag any shallower layer "SHALLOW - deeper cause at file:function"). D4 ADVERSARIAL HIDDEN-ORACLE REPRO (the most adversarial maintainer assertion from the issue title+text alone, a binding repro you may NOT phrase as the patch's own mechanism, proven RED against UNPATCHED code with captured output). D5 VERDICT - PASS only when the frozen fix LAYER == your D3 AND the D4 repro is RED unpatched; else REJECT - depth-miss to G1. CRITICAL: read the proposed fix layer ONLY to compare against your own independently-derived D3 - NEVER to seed D1-D3.
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.
- 9d ago First seen · 27 lines · 62 tokens per session scan A 36d62e2f842c
ap-depth-prober is an agent published in the GitHub repository Spielewoy/autoprompt-skill (1,019 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 874 once invoked, about $0.0003 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 agents, from other repositories
debugger
Specialized debugging agent. Use when facing hard bugs, test failures, or runtime errors that need systematic investigation.
factory-ci-doctor
Diagnostician for one red GitHub Actions run. Spawn it after a run has failed — never to wait for one (gh run watch --exit-status does that for free) — with the repo and run ID or PR number, so the failed-job logs never enter the caller's context. It returns the culprit job/step, the offending log lines, and a TICKET…
reference-refuter
Adversarial close-gate for a reference module. Given a module path, tries to REFUTE its claims against the code, the database and the tree. Returns a verdict per claim. Never rewrites the document.
symlink-checker
Verifies all symlinks in .claude/ resolve to valid targets.
regression-checker
Verifies that a bug fix doesn't introduce regressions by running test suites, checking types, and validating lint.
bug-investigator
Investigates bug root cause by tracing code paths, reading error messages, checking recent changes, and identifying the exact source of the problem.