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-verify.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-verify)<a href="https://agentmods.dev/commands/littlebearapps/untether/step-verify"><img src="https://agentmods.dev/badge/commands/littlebearapps/untether/step-verify/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-verify"><img src="https://agentmods.dev/badge/commands/littlebearapps/untether/step-verify.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 | $0.01621 |
| Opus 5.5 | $0.00000 | $0.00648 |
| Sonnet 5.5 | $0.00000 | $0.00324 |
| Haiku 4.5 | $0.00000 | $0.00162 |
Grade A, and why
step-verify scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- The targeted event signature (e.g. `subprocess.liveness_stall`) — should How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 8 — Post-fix health check
Confirm the fix worked. Confirm no regression. Attest. Roll the fleet only after the gate is satisfied.
This file expands the parent command's Step 8 summary. The "fix is verified" bar is high — a passing test suite is necessary but not sufficient.
1. Restart untether-dev and tail logs
# NEVER restart untether.service (staging) here. Always untether-dev.
systemctl --user restart untether-dev
journalctl --user -u untether-dev -f
In the tail, watch for:
- The targeted event signature (e.g.
subprocess.liveness_stall) — should be absent for sessions exhibiting the same input shape that previously triggered it. - New error signatures — if you fixed one thing and broke another, the new signature surfaces here.
- Auto-continue chatter — should be quiet for normal completions; firing
only when the upstream Claude bug surfaces (
last_event_type=user).
If the fix is for a chat-side issue (control-channel, telegram-transport),
also re-run the affected interaction via @untether_dev_bot and confirm
visually.
2. Run integration tests at the right tier
From docs/reference/integration-testing.md and
.claude/rules/release-discipline.md:
| Change scope | Required tiers | Time |
|---|---|---|
| Patch (bug fix) | Tier 7 (command smoke) + Tier 1 (affected engine + Claude) + relevant Tier 6 (stress) | ~30 min |
| Minor (new feature) | Tier 7 + Tier 1 (all 4 supported engines) + Tier 2 (Claude interactive) + Tier 3 (transport if changed) + Tier 4 (overrides if changed) + Tier 6 + upgrade path | ~75 min |
| Major (breaking) | ALL tiers (1–7), all supported engines, full upgrade path | ~120 min |
Integration tests are automated via Telegram MCP tools (send_message,
get_history, list_inline_buttons, press_inline_button,
reply_to_message, send_voice, send_file) + Bash (journalctl,
kill -TERM, FD/zombie checks). Chat IDs in
docs/reference/integration-testing.md §Test chats.
Use @untether_dev_bot. NEVER test on @hetz_lba1_bot (staging) until
dev tests pass.
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 4021f45e18ea
- 1mo ago First seen · 170 lines · 0 tokens per session scan A 695bcee83753
step-verify 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 1,621 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
test
Design or run focused test validation for a task, bug, or diff.
automated-smoke-test
Run automated smoke test using engine MCP.
prp-implement
Execute an implementation plan with rigorous validation loops.
qa-plan
Generate QA test plan for sprint or feature.
regression-suite
Map test coverage to GDD critical paths.
skill-improve
Improve skill using test-fix-retest loop.