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.
npx agentmods add commands/littlebearapps/untether/docsgit clone --depth 1 https://github.com/littlebearapps/untetherWhat 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 | $0.00027 | $0.01110 |
| Opus 5 | $0.00014 | $0.00555 |
| Sonnet 5 | $0.00005 | $0.00222 |
| Haiku 4.5 | $0.00003 | $0.00111 |
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 yesterday.
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 + `CLAUDE.md
Testsas 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/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 is gate-protected.
docs/faq/faq.mdaccepts Edit/Write/append but blocksrm/mv/>(thehelp-faq-protect.shhook). Never delete/move it. - 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 ## Tests) |
/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? CLAUDE.md## Tests: does the list matchtests/reality? Any new test file undocumented?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.
- yesterday First seen · 84 lines · 27 tokens per session scan A c77fa2995431
docs is a command published in the GitHub repository littlebearapps/untether (66 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 1,110 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
psm
/oh-my-claudecode:psm is a compatibility alias for /oh-my-claudecode:project-session-manager.
release
Ship a stable cmux release built by CI: bump version, update changelog, open a PR, merge, tag, then GitHub Actions builds, signs, and publishes.
release
This compatibility command keeps /oh-my-claudecode:release available without loading the full release skill description in every Claude Code session.
self-improve
This compatibility command keeps /oh-my-claudecode:self-improve available without loading the full self-improve skill description in every Claude Code session.
research
Research a technical or product question.
wtfp:discuss-section
Capture the researcher's intended purpose, essential content, voice, and boundaries before planning.