diagnose-loop

A set of instructions for investigating Soothe agent loops, meaning repeated automated work cycles. It reads Soothe logs and examines plans, task lists, tool calls, and loaded skills.

In plain words
What is it for?
Use it to diagnose a specific loop or broad Soothe activity, inspect daemon and runner logs, investigate tool errors, and check plan, todo, and skill behavior.
Why use it?
It helps locate the cause of hangs, failed steps, missing progress, repeated tool use, inefficient plans, or skills that were not applied.

Skill for Claude CodeCodex

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 skills/mirasoth/soothe/diagnose-loop
Any agent
npx skills add mirasoth/soothe --skill diagnose-loop
Clone the repo
git clone --depth 1 https://github.com/mirasoth/soothe

Made for: Claude Code, Codex.

Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,529 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.

ModelPer sessionOnce invoked
Fable 5 $0.00107 $0.02529
Opus 5 $0.00053 $0.01264
Sonnet 5 $0.00021 $0.00506
Haiku 4.5 $0.00011 $0.00253

Measured 2d ago against content hash a921630a07d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

.agents/skills/diagnose-loop/SKILL.md · 251 lines

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:name failed, 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*

Read the full file on GitHub · 251 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.

  1. 2d ago First seen · 251 lines · 107 tokens per session scan A a921630a07d5

Subscribe to this mod's changes

diagnose-loop is a skill published in the GitHub repository mirasoth/soothe (10 stars, last pushed 3d ago), licensed MIT. It adds 107 tokens to every session and 2,529 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.

Related

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.

ruvnet/metaharness · 66 tokens

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…

ruvnet/metaharness · 89 tokens

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.

ruvnet/metaharness · 85 tokens

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…

ruvnet/metaharness · 90 tokens

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.

ruvnet/metaharness · 79 tokens

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.

ruvnet/metaharness · 73 tokens