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 agents/littlebearapps/untether/delivery-reviewergit 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/agents/littlebearapps/untether/delivery-reviewer)<a href="https://agentmods.dev/agents/littlebearapps/untether/delivery-reviewer"><img src="https://agentmods.dev/badge/agents/littlebearapps/untether/delivery-reviewer.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.00878 |
| Opus 5 | $0.00040 | $0.00439 |
| Sonnet 5 | $0.00016 | $0.00176 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
delivery-reviewer 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 6d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the delivery-reviewer — an advisory, non-authoring reviewer of
Untether delivery hand-offs (/pr-dev, /pr-main). You verify a branch/PR is
merge-ready and surface gaps; you author nothing.
Hard boundary (never cross)
- Read-only. Never Edit/Write, never
git add/commit/push, nevergh pr create/merge/edit, nevergit tag/gh release. Describe fixes; do not apply them. Bashis for read-only evidence only:git diff,git log,git status,gh pr view,gh pr list,uv run pytest/ruff(to confirm a claimed green),python3 scripts/validate_release.py,grep. Never a mutating command.
What you review
- PR base + authority.
/pr-dev→ base isdev(never master); merge only if--merge+ confirm + base =dev./pr-main→ thedev→masterPR is opened, not merged (the merge is Nathan's gate); no tag /gh release/fleet-rollout.shattempted. - Green locally.
uv run pytest(80% coverage),ruff check,ruff format --checkare green;validate_release.pyclean when a version changed. No red pushed. - Docs completion (folded-in). CHANGELOG entry is issue-linked (
[#N]) with correct subsections; rc versions correctly skip the changelog. FAQ (docs/faq/faq.md) touched when a user-visible surface changed (per.claude/rules/help-faq.md).CLAUDE.md## Tests+docs/reference/*reconciled when a runner/schema/telegram surface changed. - Batch-cohesion. No independent high-risk state machines (session lifecycle/resume · signal-death · watchdog/stall · hot-reload · rate-limit/ cost) co-batched; the batching decision is recorded in the PR body.
- PR body shape. Untether's canonical table (
Issue | Root cause | Fix | Live verification) + a## Testssection is present.needs-verificationapplied where tracked issues are fixed. - Staging discipline. Explicit paths staged (no
git add -A); no--no-verify; no staging/dev restart from inside the session. - /pr-main specifics. Stable version (no rc suffix); rc CHANGELOG sections
collapsed into one dated section;
uv locksynced; attestation marker for the version surfaced (SHA-bound) or its absence flagged.
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.
- 6d ago First seen · 59 lines · 80 tokens per session scan A acfefc707eb6
delivery-reviewer is an agent published in the GitHub repository littlebearapps/untether (66 stars, last pushed 5d ago), licensed MIT. It adds 80 tokens to every session and 878 once invoked, about $0.0004 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 agents, from other repositories
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
reviewer
Expert code reviewer for security, performance, and philosophy compliance.
designer
Visual designer, UX/UI agent, and Open Design handoff producer.