Borrowing it
Nothing to install: this file belongs to littlebearapps/untether. 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/littlebearapps/untether/master/.claude/commands/debug/step-research.mdgit clone --depth 1 https://github.com/littlebearapps/untetherWrote 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/commands/littlebearapps/untether/step-research)<a href="https://agentmods.dev/commands/littlebearapps/untether/step-research"><img src="https://agentmods.dev/badge/commands/littlebearapps/untether/step-research/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/commands/littlebearapps/untether/step-research"><img src="https://agentmods.dev/badge/commands/littlebearapps/untether/step-research.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 | $0.00000 | $0.01697 |
| Opus 5.5 | $0.00000 | $0.00679 |
| Sonnet 5.5 | $0.00000 | $0.00339 |
| Haiku 4.5 | $0.00000 | $0.00170 |
Grade A, and why
step-research 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 18d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 3 — Research
Always research before proposing a fix. The Untether bug you're chasing is often a known upstream engine quirk, a previously-fixed regression, or a documented config gotcha.
3a. Untether docs
| Path | What it covers |
|---|---|
docs/reference/runners/claude/runner.md |
Claude Code runner spec — CLI invocation, control channel, permission modes |
docs/reference/runners/claude/stream-json-cheatsheet.md |
Claude JSONL event shapes |
docs/reference/runners/claude/untether-events.md |
Claude → Untether event translation rules |
docs/reference/runners/codex/*.md |
Codex runner spec + JSONL + translation |
docs/reference/runners/opencode/*.md |
OpenCode runner spec + JSONL + translation |
docs/reference/runners/pi/*.md |
Pi runner spec + JSONL + translation |
docs/reference/runners/gemini/*.md |
Gemini runner spec + JSONL + translation (deprecated, unsupported — no fixes) |
docs/reference/runners/amp/*.md |
AMP runner spec + JSONL + translation (deprecated, unsupported — no fixes) |
docs/reference/transports/telegram.md |
Telegram transport — Bot API client, outbox, voice, forum topics |
docs/reference/modes.md |
Workflow modes (assistant / workspace / handoff) |
docs/reference/dev-instance.md |
Dev vs staging service quickref + staging workflow |
docs/reference/integration-testing.md |
Per-tier integration test playbook |
.claude/rules/*.md |
Project rule files (auto-load on edits to matching paths) |
.claude/skills/*/SKILL.md |
Project skills — telegram-bot-api, jsonl-subprocess-runner, claude-stream-json, codex-opencode-pi, untether-architecture, release-coordination |
Read the relevant file before proposing any change. Untether docs are deliberately concrete — they contain code paths, event names, config keys.
3b. Closed Untether issues (regression detection)
SINCE=$(date -u -d '90 days ago' +%Y-%m-%d)
gh issue list --repo littlebearapps/untether \
--search "closed:>=${SINCE}" --state closed \
--json number,title,closedAt,labels,milestone \
--limit 100
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.
- 18d ago Changed 8b9c8cf6a82c
- 1mo ago First seen · 138 lines · 0 tokens per session scan A a2a447193549
step-research is a command published in the GitHub repository littlebearapps/untether (74 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,697 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.
Other commands, from other repositories
root-cause
Use when any test fails, bug appears, or behaviour surprises you, before proposing a fix - find the cause and prove it, by reading real evidence, tracing bad values back to their origin, comparing against a working case, and testing one hypothesis at a time.
refactor
Refactor and optimize [code].
hotfix
Emergency fix workflow with audit trail.
kotlin-build
Fix Kotlin/Gradle build errors, compiler warnings, and dependency issues incrementally. Invokes the kotlin-build-resolver agent for minimal, surgical fixes.
bug-report
Create structured bug report.
wtfp:report-bug
Collect a reproducible bug report and publish it only after explicit user approval.