Borrowing it
Nothing to install: this file belongs to mirasoth/soothe. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mirasoth/soothe/main/.agents/skills/inspect-autopilot-job/SKILL.mdgit clone --depth 1 https://github.com/mirasoth/sootheWrote 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/mirasoth/soothe/inspect-autopilot-job)<a href="https://agentmods.dev/skills/mirasoth/soothe/inspect-autopilot-job"><img src="https://agentmods.dev/badge/skills/mirasoth/soothe/inspect-autopilot-job/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/mirasoth/soothe/inspect-autopilot-job"><img src="https://agentmods.dev/badge/skills/mirasoth/soothe/inspect-autopilot-job.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 | $0.00095 | $0.03884 |
| Opus 5 | $0.00048 | $0.01942 |
| Sonnet 5 | $0.00019 | $0.00777 |
| Haiku 4.5 | $0.00010 | $0.00388 |
Grade A, and why
inspect-autopilot-job 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 10d 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inspect Autopilot Job
Job-scoped forensics for Autopilot + LoopRail. For single-loop StrangeLoop /
tools / plans / skills, use diagnose-loop
Workflow B on hot autopilot__{job}__* loops.
Prefer .venv/bin/soothe when available.
When to Use
- Job id / 8-char prefix / child goal id under a rail job
- Low parallelism, pending implement goals, rail not advancing
- Integrate / commit / review / QA / feedback stuck
- “What happened on this job?” / DAG structure / execution history
- Consensus send_backs, engine recoveries, pruned makers
Data Sources
| Source | Path / command | Use |
|---|---|---|
| Live DAG | soothe autopilot job|goal|status|top |
Current status (authoritative when daemon up) |
| Job contract | ~/.soothe/data/jobs/{job}/GOAL.md |
Submit description snapshot (IG-702) |
| Rail state | ~/.soothe/data/jobs/{job}/rail_state.json |
rail_id, wave/feedback rounds, annotations (role/tags/branch) |
| Rail trace | …/jobs/{job}/rail_trace.jsonl (legacy: loops/{job}/) |
Builtin fires + guards; phase timeline |
| Job↔loops | persist.db autopilot:job_loops:{job} (ns autopilot_goals) |
Per-goal attempt history + wall times |
| Goals snapshot | persist.db autopilot:goals:snapshot |
Offline DAG (may lag live CE) |
| Dispatch logs | soothe.log*: dispatched goal, Consensus, Sent goal, Engine recovering |
Send_backs / recovery |
| Worker logs | ~/.soothe/data/loops/autopilot__{job}__*/runner.log |
Per-attempt StrangeLoop detail |
SQLite keys use namespace autopilot_goals:
sqlite3 ~/.soothe/data/databases/persist.db \
"SELECT data FROM soothe_kv WHERE namespace='autopilot_goals' AND key='autopilot:job_loops:$JOB';"
Workflow
1. Resolve job id (C0)
2. Live DAG + rail_state annotations (structure)
└─ 1a. CE goal DAG analysis + digraph (required) ← topology, cycles,
orphans, root-wiring, ready/blocked, critical path, DOT/mermaid/ASCII
3. Goal execution history (job_loops + phases) ← required
4. Parallelism scorecard
5. Rail conformance (builtin seq vs rail YAML)
6. Failure / recovery modes
7. Optional: diagnose-loop Workflow B on hot loops
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 348 lines · 95 tokens per session scan A d3b56a0052f4
inspect-autopilot-job is a skill published in the GitHub repository mirasoth/soothe (10 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 3,884 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.
create-harness
Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a…
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
oia-manifest
Emit .harness/oia-manifest.json declaring layer alignment with the OIA v0.1 9-layer reference architecture. Self-describes the harness's MCP wiring, witness signing, audit log, identity posture (always 'none' at v0.1). --check verifies an existing manifest, --dry-run prints without writing, --json emits to stdout.
repo-genome
7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.
example-harness
Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming…