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/docs.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/docs)<a href="https://agentmods.dev/commands/littlebearapps/untether/docs"><img src="https://agentmods.dev/badge/commands/littlebearapps/untether/docs/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/docs"><img src="https://agentmods.dev/badge/commands/littlebearapps/untether/docs.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 | $0.00091 | $0.01131 |
| Opus 5.5 | $0.00036 | $0.00452 |
| Sonnet 5.5 | $0.00018 | $0.00226 |
| Haiku 4.5 | $0.00009 | $0.00113 |
Grade A, and why
docs 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are handling /docs. /docs reconciles Untether's small doc surface
outside a PR. It is an escape hatch, not the default path — docs
completion is normally folded into /pr-dev (CHANGELOG + FAQ + docs/reference/test-catalog.md
as a completion criterion). Reach for /docs only when documentation
has drifted on its own and there is no code change to deliver alongside it.
User input: $ARGUMENTS
Untether adaptations (read first)
Load .claude/rules/workflow-commands.md (routing + cross-cutting rules),
.claude/rules/help-faq.md, and .claude/rules/context-quality.md. Key points:
- Authority: docs only. Edit CHANGELOG /
docs/faq/faq.md/CLAUDE.md(keep it under its ~200-line budget) /docs/reference/*. Never code, never a PR (if a code branch is involved → route to/pr-dev, which folds docs in), never master/tag/release. - If a code change is in flight → STOP and route to
/pr-dev. Do not split docs for a code change into a separate PR — that fragments delivery. - FAQ must stay put. Edit/Write/append
docs/faq/faq.mdfreely, but neverrm/mv/>it (thehelp-faq-protect.shhook blocks that). - Confirm-gated + idempotent. Surface the drafted edits and wait for a tap; re-running must not duplicate a CHANGELOG entry or FAQ Q/A.
When to use (vs /pr-dev)
| Situation | Command |
|---|---|
| Delivering code + its docs | /pr-dev (docs folded in) |
A doc drifted with no code change (stale FAQ, missing CHANGELOG link, out-of-date docs/reference/test-catalog.md) |
/docs |
Reconciling docs/reference/* after a runner/schema change already merged |
/docs |
Flow
X-1. Scan for drift
git diff/git logsince the last doc touch; check the CHANGELOG against recent merges (issue links present?### fixes/changes/…correct?).- FAQ: scan
docs/faq/faq.mdagainst current features perhelp-faq.md— any user-visible surface (engine support, auth/billing, privacy, approval semantics, cost, voice, install/update) answered wrongly? docs/reference/test-catalog.md: does it matchtests/reality? Any new test file undocumented? IsCLAUDE.mdstill within budget (no feature/test lists re-grown)?docs/reference/*: any runner/schema/telegram doc lagging code?
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 · +64 tokens per session 1f35accdebbe
- 1mo ago First seen · 84 lines · 27 tokens per session scan A c77fa2995431
docs is a command published in the GitHub repository littlebearapps/untether (74 stars, last pushed today), licensed MIT. It adds 91 tokens to every session and 1,131 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 2026-08-30.
Other commands, from other repositories
psm
/oh-my-claudecode:psm is a compatibility alias for /oh-my-claudecode:project-session-manager.
research
Research a technical or product question.
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.
sprint-plan
Generate or update sprint plan.
tech-debt
Track and prioritize technical debt.
santa-loop
Adversarial dual-review convergence loop — two independent model reviewers must both approve before code ships.