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/skills/claude-stream-json/SKILL.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/skills/littlebearapps/untether/claude-stream-json)<a href="https://agentmods.dev/skills/littlebearapps/untether/claude-stream-json"><img src="https://agentmods.dev/badge/skills/littlebearapps/untether/claude-stream-json/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/skills/littlebearapps/untether/claude-stream-json"><img src="https://agentmods.dev/badge/skills/littlebearapps/untether/claude-stream-json.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 | $0.00065 | $0.03778 |
| Opus 5.5 | $0.00026 | $0.01511 |
| Sonnet 5.5 | $0.00013 | $0.00756 |
| Haiku 4.5 | $0.00006 | $0.00378 |
Grade C, and why
claude-stream-json scanned grade C with 2 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"tool_name":"Bash","input":{"command":"rm -rf /"},"permission_suggestions":[...]}} Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
ClaudeRunner uses `pty.openpty()` instead of `subprocess.PIPE` for stdin: How it starts
The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code stream-json Protocol (Consumer)
Untether spawns Claude Code CLI as a subprocess and consumes its JSONL output. This skill covers the protocol from Untether's perspective.
Key files
| File | Purpose |
|---|---|
src/untether/runners/claude.py |
ClaudeRunner — subprocess management, PTY, control channel, event translation |
src/untether/schemas/claude.py |
msgspec structs for Claude JSONL events |
src/untether/runners/tool_actions.py |
tool_kind_and_title() — tool name to ActionKind mapping |
src/untether/loop_scheduler.py |
Loop mode: Untether-run /loop schedules, wake-up timers, cancel and cron-suppression records (#925, #926) |
docs/reference/runners/claude/runner.md |
Full runner specification |
docs/reference/runners/claude/stream-json-cheatsheet.md |
JSONL event shapes with examples |
docs/reference/runners/claude/untether-events.md |
Claude JSONL to Untether event mapping |
.claude/skills/claude-stream-json/control-channel-internals.md |
Control-channel mechanism detail: registries, claims, live-session stdin writers, async-hook hold, scheduling hooks, plan re-arm, parent-initiated requests |
CLI invocation
Non-interactive mode (-p)
claude -p --output-format stream-json --input-format stream-json --verbose -- <prompt>
-p/--print: non-interactive, prompt as positional arg after----verbose: required for full stream-json output--input-format stream-json: enables JSON input on stdin- Prompt passed after
--to protect prompts starting with-
Interactive permission mode
claude --output-format stream-json --input-format stream-json --verbose \
--permission-mode plan --permission-prompt-tool stdio
- No
-pflag — prompt sent via stdin as JSON user message --permission-prompt-tool stdio: enables bidirectional control channel--permission-mode <mode>: the configured mode verbatim (plan,auto,default,acceptEdits, …); only Untether'splan-autois translated (toplan, #741)--include-hook-eventswhen the cachedclaude --helpprobe lists it (#812)- The stdin
initializerequest carrieshooks: exact-namePreToolUsematchers forCronCreate/CronDelete(callback idsut_loop_cron_create/ut_loop_cron_delete, #925) unless[loop] own_schedule = false - A session that may still hold a native CLI cron job is resumed with
CLAUDE_CODE_DISABLE_CRON=1(#926)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · +67 lines c6a12d9b1c98
- 1mo ago First seen · 241 lines · 65 tokens per session scan C 1bdef80013d8
claude-stream-json is a skill published in the GitHub repository littlebearapps/untether (74 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 3,778 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orca-emulator-android
Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
awardwallet
Query AwardWallet for loyalty program balances, elite status, and transaction history. Use when checking points inventory, airline status, or planning trips on points.
atlas-obscura
Search Atlas Obscura for weird, wonderful, and hidden gem places near any destination. Find the interesting stuff, not boring plaques. Search by coordinates, get full details with descriptions and images.