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/pr-devgit 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 | $0.00058 | $0.01976 |
| Opus 5 | $0.00029 | $0.00988 |
| Sonnet 5 | $0.00012 | $0.00395 |
| Haiku 4.5 | $0.00006 | $0.00198 |
Grade A, and why
pr-dev 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.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are handling /pr-dev. /pr-dev takes a feature/fix/chore branch from
"code + tests done" to ONE merge-ready PR to dev (→ TestPyPI on merge). Docs
reconciliation is a completion criterion here, not a separate /docs stage.
This is the everyday delivery command and Untether's batch-PR unit.
User input: $ARGUMENTS
Untether adaptations (read first)
Load .claude/rules/workflow-commands.md (routing + cross-cutting rules) and
.claude/rules/release-discipline.md (changelog/version/FAQ discipline). Key
points:
- Release-guard obedience. PR to
devonly.gh pr merge --squashis allowed only with base =dev(the one merge Claude may do). Never push/merge tomaster, nevergit tag, nevergh release create, never--no-verify. The GitHub branch ruleset + CODEOWNERS is the real gate; the local hooks are defense-in-depth. - Dev/staging separation. Never
systemctl restartstaging or dev from inside this session (hot-reload drain drops the final message). - Confirm-gated + idempotent. Surface the drafted PR body and wait for a tap;
de-dupe against an existing open PR for this branch; a re-invoked
/pr-devmust not double-open or double-merge. - Redaction. Scrub tokens/keys/env/chat-content/fleet identifiers from any evidence quoted in the PR body.
- Untether-mode.
--mergeconfirmation is stated in text and STOPS for a reply. Keep the report brief.
Sub-commands
| Form | Action |
|---|---|
/pr-dev (no args) |
Finalise the current branch → open a PR to dev (stops merge-ready) |
/pr-dev --rc X.Y.ZrcN |
Cut a staging rc bump (chore: staging X.Y.ZrcN) → PR to dev |
/pr-dev --dry-run |
Gate + local checks + print what would happen; open/push nothing |
/pr-dev --merge |
Squash-merge the PR to dev only (confirm-gated) → TestPyPI CI |
/pr-dev --help |
Usage, then stop |
Flow
D-1. Assert a clean, valid starting point
git statusclean (or only the intended staged paths); resolve the branch.- Refuse if the branch is
master/main→ STOP (a delivery branch is required). Confirm it is ahead ofdev.
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.
- 2d ago First seen · 145 lines · 58 tokens per session scan A 8cd5f41af556
pr-dev is a command published in the GitHub repository littlebearapps/untether (66 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 1,976 once invoked, about $0.0003 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.