passthrough

A command for allowing the next Bash command to run outside the try sandbox once. Its effects are written directly to the real filesystem.

In plain words
What is it for?
Use it before a specific Bash command that you intentionally want to execute without sandbox wrapping.
Why use it?
It provides a deliberate one-command bypass when a task cannot or should not run inside the sandbox.

Command

Install

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.

agentmods
npx agentmods add commands/binpash/trai/passthrough
Clone the repo
git clone --depth 1 https://github.com/binpash/trai
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 122 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00122
Opus 5 $0.00007 $0.00061
Sonnet 5 $0.00003 $0.00024
Haiku 4.5 $0.00001 $0.00012

Measured 2d ago against content hash dcd15fde01de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

passthrough 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.

commands/passthrough.md · 13 lines

What it actually says

Set a one-shot bypass token. The NEXT Bash command Claude runs in this session will NOT be wrapped in try — its effects will land on the real filesystem. The token is consumed after one use.

Use this sparingly: for commands you deliberately want to apply without review.

!${CLAUDE_PLUGIN_ROOT}/scripts/cmd-passthrough.sh

Changes

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.

  1. 2d ago First seen · 13 lines · 14 tokens per session scan A dcd15fde01de

Subscribe to this mod's changes

passthrough is a command published in the GitHub repository binpash/trai (5 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 122 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 2026-08-31.