README

A guide to the files that define Untether’s eight-step deep-debugging process, with one file assigned to each investigation stage.

In plain words
What is it for?
Use it to find the correct checklist before investigating an issue or changing the debugging workflow.
Why use it?
It gives agents one maintained source for classification, evidence gathering, research, fixing, and verification instructions.

Command for Claude Code

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 commands/littlebearapps/untether/readme
Clone the repo
git clone --depth 1 https://github.com/littlebearapps/untether

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 821 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 $0.00000 $0.00821
Opus 5 $0.00000 $0.00411
Sonnet 5 $0.00000 $0.00164
Haiku 4.5 $0.00000 $0.00082

Measured 2d ago against content hash bd9511b881b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

README 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.

.claude/commands/debug/README.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/debug companion bundle

This directory is the canonical source for each step of Untether's 8-step deep debugging protocol. The parent command file at ../debug.md orchestrates the steps; each file here owns the detail for one step (or one shared output).

Edit a file here to update the rule for that step everywhere — the parent command references these by path and does not duplicate their content.

Files

File Owns Read before
step-classify.md Step 1 — 15 Untether issue classes + diagnostic hints Picking a class
step-evidence.md Step 2 — data-source catalogue (journalctl, structlog, fleet SSH, MCP, state files) Running any evidence command
step-research.md Step 3 — docs, closed issues, upstream engine repos, library docs Researching prior art
systemic-patterns.md Step 4 — known Untether patterns + memory-aware exceptions Scoring any signal in sweep, OR filing/escalating in targeted
step-fix.md Step 7 — implementation checklist + branch model + release guard Writing any code change
step-verify.md Step 8 — post-fix verification (dev restart, integration tests, attestation, fleet rollout) Declaring an issue verified
output-template.md Output formats — Debug Report (targeted), Triage Report (sweep), Verification Spec Emitting any user-facing report

External references reused (not duplicated)

Path Purpose
~/.claude/commands/monitor/severity-rubric.md Severity buckets and label routing
~/.claude/commands/monitor/signal-categories.md Bug + enhancement signal taxonomy
../../rules/runner-development.md Runner contract: 3-event sequence, session locking, signal-death handling
../../rules/telegram-transport.md Outbox model, callback_data limits, ephemeral cleanup
../../rules/control-channel.md PTY lifecycle, session registries, cooldown, ask-question flow
../../rules/dev-workflow.md Dev/staging separation — NEVER restart staging to test
../../rules/release-discipline.md Branch model, integration test gate, fleet rollout
../../rules/testing-conventions.md pytest patterns, stub subprocess scripts
../../rules/help-faq.md FAQ touch-up checklist on releases
../../rules/context-quality.md Cross-file consistency rules
../../../docs/reference/integration-testing.md Per-tier integration test playbook
../../../docs/reference/dev-instance.md dev vs staging service quickref

Read the full file on GitHub · 50 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 · 50 lines · 0 tokens per session scan A bd9511b881b7

Subscribe to this mod's changes

README is a command published in the GitHub repository littlebearapps/untether (66 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 821 tokens. 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.