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 skills/littlebearapps/untether/codex-opencode-pinpx skills add littlebearapps/untether --skill codex-opencode-pigit 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 | $0.00053 | $0.02262 |
| Opus 5 | $0.00026 | $0.01131 |
| Sonnet 5 | $0.00011 | $0.00452 |
| Haiku 4.5 | $0.00005 | $0.00226 |
Grade A, and why
codex-opencode-pi 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex, OpenCode, and Pi Runner Protocols
These three engines are non-interactive only — no control channel, no permission prompts. They extend JsonlSubprocessRunner directly (unlike ClaudeRunner which overrides run_impl).
Quick comparison
| Aspect | Codex | OpenCode | Pi |
|---|---|---|---|
| CLI | codex exec --json |
opencode run --format json |
pi --print --mode json |
| Event model | Turn-based (items in turns) | Step-based (tools in steps) | Agent-based (messages + tools) |
| Resume line | `codex resume <thread_id>` |
`opencode --session ses_XXX` |
`pi --session <token>` |
| Resume token | thread_id (UUID) | ses_XXXX (26+ chars) | UUID short (8 chars) or path |
| Final answer | agent_message item |
Accumulated text events |
message_end assistant content |
| Error signal | turn.failed |
error event / missing step_finish |
stopReason in message_end |
Codex
Key files
| File | Purpose |
|---|---|
src/untether/runners/codex.py |
CodexRunner implementation |
src/untether/schemas/codex.py |
msgspec structs for Codex events |
docs/reference/runners/codex/exec-json-cheatsheet.md |
JSONL event shapes |
docs/reference/runners/codex/untether-events.md |
Event mapping spec |
CLI invocation
codex exec --json --skip-git-repo-check --color=never \
[--model MODEL] [--session THREAD_ID -] [-]
- Prompt on stdin (trailing
-means read stdin) - Resume:
--session <thread_id> - --skip-git-repo-check --color=neverfor clean output
JSONL events
| Event | Untether mapping |
|---|---|
thread.started |
StartedEvent(resume=thread_id) |
item.started |
ActionEvent(phase="started") |
item.updated |
ActionEvent(phase="updated") |
item.completed |
ActionEvent(phase="completed") |
turn.completed |
CompletedEvent(ok=True, answer=final_answer) |
turn.failed |
CompletedEvent(ok=False, error=message) |
error (transient) |
Progress note (reconnect handling) |
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 · 240 lines · 53 tokens per session scan A a278a8b17922
codex-opencode-pi is a skill published in the GitHub repository littlebearapps/untether (66 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 2,262 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 skills, from other repositories
cmux-localization
Localization rules and audit workflow for cmux UI strings, settings rows, menus, shortcuts, schema/config text, docs, command/help text, alerts, tooltips, and web messages. Use whenever changing user-facing text.
translate-craft
Professional translation and localization for 8 languages (ES, JA, FR, DE, PT, ZH, KO, AR). Covers tone matrix, formality levels, i18n patterns (react-intl, i18next, ICU), RTL layout, cultural adaptation, and locale formatting. Use when user asks to translate text, localize an app, adapt tone, review translations, add…
new-adapter
Add support for a new AI tool with adapters, CLI, completion, and tests.
sync-readme
Synchronize English README.md with Chinese READMEZH.md, maintaining content parity.
repo-readme-assets
README.md (EN) + localized mirror + local animated SVG header/footer for a repository. Generates assets/header.svg and assets/footer.svg with SMIL animation (4 presets: default/minimal/dark-first/monochrome), zero external services. Scripts: generateassets.py, validatesvg.py, extractcontext.py. Triggers: 'readme…
debug-bug
Systematically investigate and fix bugs using token-efficient context gathering. Reproduces the issue first, localizes with blame and history, traces the call path, then verifies the fix. Use when asked to fix a bug, investigate an error, or debug unexpected behavior.