signal copilot-instructions.md

signal copilot-instructions.md is an instructions file for GitHub Copilot from mattbaconz/signal. It costs 392 tokens per session, scanned A, original, MIT.

Workspace instructions for Signal, a system that controls how an agent responds and saves progress. They define response styles, checkpoints, workflow commands, and coding practices.

In plain words
What is it for?
Use them when following Signal response modes, saving checkpoints, running its workflow commands, or making code changes in the Signal repository.
Why use it?
They keep responses consistent across sessions and help preserve progress during longer work. They also specify which generated files to edit and which checks to run before changes are committed.

Instructions file for GitHub Copilot

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 instructions/mattbaconz/signal/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/mattbaconz/signal

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for signal copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mattbaconz/signal/copilot-instructions.svg)](https://agentmods.dev/instructions/mattbaconz/signal/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/mattbaconz/signal/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/mattbaconz/signal/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 392 This file is loaded in full into every session.
When invoked 392 The same file — it is already loaded in full.
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 5.1 $0.00392 $0.00392
Opus 5 $0.00196 $0.00196
Sonnet 5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 5d ago against content hash 3df5434f72b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

signal copilot-instructions.md 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 5d 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.

.github/copilot-instructions.md · 19 lines

What it actually says

SIGNAL — always-on (workspace)

Canonical source: templates/host-always-on.body.md — run scripts/sync-host-integrations.ps1 after edits. Generated files are copies; do not edit them by hand.

Full protocol: signal/SKILL.md · Root README.md (When to use which tier, token metrics, benchmarks).

Session defaults

  • Default SIGNAL-3 for every reply: terse, no preamble, no hedging; fragments OK. Non-obvious claims → [0.0–1.0]. Auto-ckpt every 5 turns.
  • No per-turn prefix is required. Treat signal3, SIGNAL-3, and /signal3 as the same reset to S3.
  • Tiers: follow the signal skill — /signal, /signal2, /signal3 when the user explicitly changes intensity.
  • Workflow skills when asked: signal-commit, signal-push, signal-pr, signal-review, signal-ckpt, signal-compress (scripts support --dry / --draft).
  • Never compress: code blocks, file paths, line numbers, quoted errors, technical terms.
  • Implementation / code edits: apply Karpathy-style coding norms from karpathy-coding-norms.md (think before coding, simplicity, surgical changes, goal-driven execution) in addition to tier defaults—not for pure chat-only compression.
  • If the model cannot comply with the active template: one line SIGNAL_DRIFT: <reason>.
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. 5d ago First seen · 19 lines · 392 tokens per session scan A 3df5434f72b6

Subscribe to this mod's changes

signal copilot-instructions.md is an instructions file published in the GitHub repository mattbaconz/signal (10 stars, last pushed 2mo ago), licensed MIT. It adds 392 tokens to every session, about $0.0020 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.

Related

Other instructions, from other repositories