policy

A command for viewing or changing what the current coding session shares with a backchannel room, which is a separate place for passing session information.

In plain words
What is it for?
Use it to inspect the current sharing setting or update what information is relayed to the backchannel room.
Why use it?
It lets you control the session's sharing policy and see the result, although the policy is best-effort and should not be treated as protection for secrets.

Command

Part of the backchannel plugin — 7 commands, 2 hooks shipped together

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/j-ronk/backchannel/policy
Clone the repo
git clone --depth 1 https://github.com/j-ronk/backchannel

Or install backchannel, the plugin that ships this one along with the rest of its 7 commands, 2 hooks.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 116 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 $0.00012 $0.00116
Opus 5 $0.00006 $0.00058
Sonnet 5 $0.00002 $0.00023
Haiku 4.5 $0.00001 $0.00012

Measured 2d ago against content hash 187434105515, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

policy 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.

client/commands/policy.md · 9 lines

What it actually says

Show or update the share policy and relay the result. The policy guides what the agent shares each turn — but redaction is best-effort (the agent can slip), so never rely on it for hard secrets. The relay itself only ever stores ciphertext plus an opaque tag.

!"${CLAUDE_PLUGIN_ROOT}/bin/backchannel" policy "$ARGUMENTS"

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 · 9 lines · 12 tokens per session scan A 187434105515

Subscribe to this mod's changes

policy is a command published in the GitHub repository j-ronk/backchannel (1 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 116 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.