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/diagnose-loop/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/diagnose-loop)<a href="https://agentmods.dev/skills/mirasoth/soothe/diagnose-loop"><img src="https://agentmods.dev/badge/skills/mirasoth/soothe/diagnose-loop/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/diagnose-loop"><img src="https://agentmods.dev/badge/skills/mirasoth/soothe/diagnose-loop.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 | $0.00107 | $0.02530 |
| Opus 5.5 | $0.00043 | $0.01012 |
| Sonnet 5.5 | $0.00021 | $0.00506 |
| Haiku 4.5 | $0.00011 | $0.00253 |
Grade A, and why
diagnose-loop 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 15d 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose Loop
Systematic log forensics for Soothe loops, daemon lifecycle, and CLI/TUI.
For autopilot jobs (job id, rail, DAG, parallelism, goal execution history), use inspect-autopilot-job.
Routing
if user mentions job id / autopilot / rail / pool / multi-goal / "low parallelism"
/ goal DAG / job execution history
→ inspect-autopilot-job (then Workflow B here on hot loops if needed)
else if specific loop id / suffix / hang / tools / plan / skills
→ Workflow B (and A if broad)
else
→ Workflow A broad triage
Prefer the venv CLI when available (.venv/bin/soothe).
When to Use
- Loop hang, failed step, spinner stuck, or missing TUI progress
- Analyze
~/.soothe/logs/or a specific loop (UUID or 4-char suffix) - Tool errors, slow steps, repetitive tool calls
- StrangeLoop plan / CoreAgent todo waste
- Skill did not load,
/skill:namefailed, or skill instructions ignored
Not this skill: autopilot job DAG, rail conformance, pool parallelism, job-level execution history → inspect-autopilot-job.
Log Locations
| File | Logger / purpose | Loop correlation |
|---|---|---|
~/.soothe/logs/soothe.log |
soothe.* — StrangeLoop, CoreAgent, tools, planner |
4-char suffix [7cba] |
~/.soothe/logs/daemon.log |
soothe_daemon.* — WebSocket, workers |
Full UUID [loop=…] |
~/.soothe/logs/cli.log |
soothe_cli.* — connection, TUI events |
May include loop context |
~/.soothe/data/loops/{loop_id}/runner.log |
Same as soothe.log, one loop | Prefer for pooled workers |
Rotated backups: *.log.1, *.log.2, etc. Runtime defaults are daemon.log
and cli.log (not soothed.log / soothe-cli.log).
Resolve Loop Identity
User may give full UUID, 4-char suffix (7cba), or step id prefix (UZH-01).
soothe loop list
ls ~/.soothe/data/loops/ | grep -i '<suffix>'
rg '\[<suffix>\]' ~/.soothe/logs/soothe.log*
rg 'loop=.*<suffix>' ~/.soothe/logs/daemon.log*
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.
- 15d ago Changed 80cc4cbed1b9
- 2mo ago First seen · 251 lines · 107 tokens per session scan A a921630a07d5
diagnose-loop is a skill published in the GitHub repository mirasoth/soothe (13 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 2,530 once invoked, about $0.0004 per session on Opus 5.5. 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.
diagnose-loop compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| diagnose-loopmirasoth/soothe | Skill | 13 | yesterday | MIT | A | 107 | Claude Code, Codex |
| diag-harnessruvnet/metaharness | Skill | 738 | yesterday | MIT | A | 85 | Claude Code |
| C31-debugChianW/C31 | Skill | 1 | 2mo ago | MIT | A | 32 | Claude Code, Codex |
| C31-researchChianW/C31 | Skill | 1 | 2mo ago | MIT | A | 36 | Claude Code, Codex |
| gsd-map-codebaseChianW/C31 | Skill | 1 | 2mo ago | MIT | A | 65 | Claude Code, Codex |
| C31-workflow-bug-reproductionChianW/C31 | Skill | 1 | 2mo ago | MIT | A | 53 | Claude Code, Codex |
| node-connectspinabot/brigade | Skill | 11k | 3d ago | MIT | A | 79 | Claude Code, Codex |