wall-dev

A command for broadcasting a message to all teammates, optionally for a set duration. It can also clear the current shared message.

In plain words
What is it for?
Use it for release notices, deployment updates, temporary instructions, or clearing an expired team message.
Why use it?
It puts team-wide updates in one visible place instead of sending the same message separately to everyone.

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/punt-labs/biff/wall-dev
Clone the repo
git clone --depth 1 https://github.com/punt-labs/biff
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 302 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 $0.00006 $0.00302
Opus 5 $0.00003 $0.00151
Sonnet 5 $0.00001 $0.00060
Haiku 4.5 $0.00001 $0.00030

Measured 2d ago against content hash 15c48a848fa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wall-dev 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • wall — 88% identical, 4 lines differ
plugin/commands/wall-dev.md · 30 lines

What it actually says

Input

Arguments: $ARGUMENTS

Parse as one of three modes:

  1. Clear: if arguments are exactly clear → call with clear=True
  2. Post with duration: if the last token matches a duration pattern (30m, 2h, 1d, 3d), it is the duration and everything before it is the message → message="...", duration="2h"
  3. Post with default: otherwise the entire argument string is the message → message="..."

If no arguments are provided, call with no parameters (shows current wall).

Examples:

  • release freeze — do not push to mainmessage="release freeze — do not push to main"
  • deploy window open 2hmessage="deploy window open", duration="2h"
  • clearclear=true
  • (empty) → no parameters

Task

Call mcp__plugin_biff-dev_tty__wall with the parsed values. The result is already formatted by a PostToolUse hook and displayed above. Do not repeat or reformat the data. Do not send any text after the tool call.

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 · 30 lines · 6 tokens per session scan A 15c48a848fa9

Subscribe to this mod's changes

wall-dev is a command published in the GitHub repository punt-labs/biff (2 stars, last pushed 2d ago), licensed MIT. It adds 6 tokens to every session and 302 once invoked, about $0.0000 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.