signal

SIGNAL is a brutalist compression layer for agentic workflows: minified .min.md skills, a small symbol vocabulary (→ ∅ Δ ! [n]), and checkpoints instead of pasting entire threads. Dense beats polite when the meter is running.

Repo · github.com/mattbaconz/signal · Protocol · skills/signal.min.md · Symbols · skills/signal-core.min.md

Latest changes: CHANGELOG.md (v0.3.1 patch notes, v0.3.0 “Shrinking Session”, and earlier). Contributing / min skills: CONTRIBUTING.md.

Demo

Heuristic token estimates use ceil(characters / 4) — useful for comparing shapes, not billed API tokens. Full tables: Benchmark. Reproduce: scripts/benchmark.ps1.

Video/GIF: A short install or benchmark run GIF is planned; see assets/README.md to record assets/signal-demo.gif and swap it into this section later.

Before / after

Install

npx skills add mattbaconz/signal

Global:

npx skills add mattbaconz/signal -y -g

Quick start: read skills/signal.min.md → pick a tier → pull in workflow skills (signal-commit, signal-push, …) only when needed.

Commands

Tier detail: Tiers.

Repo map

There is no legacy top-level signal/ directory in this repo—ignore older docs that referred to it. This table is what you actually open after cloning.

Why SIGNAL

Long prompts and hedging eat context. SIGNAL standardizes how you shrink: symbols instead of paragraphs, .signal_state.md for durable state, signal-diff / signal-search for summarized context instead of raw dumps.

flowchart LR
  subgraph inputs [Verbose]
    V1[Long replies]
    V2[Full thread history]
    V3[Hedging and filler]
  end
  subgraph signal [SIGNAL]
    S[Symbol grammar]
    C[CKPT summaries]
    M[Minified skills]
  end
  subgraph outputs [Dense]
    D1[Terse pointers]
    D2[Checkpoint atom]
    D3[~87% smaller payloads]
  end
  V1 --> S
  V2 --> C
  V3 --> S
  S --> D1
  C --> D2
  M --> D3

Tiers

Use /signal, /signal2, or /signal3.

Symbol grammar (snippet)

Full reference: skills/signal-core.min.md.

Benchmark

Same chart as Demo; numbers below are the tables behind it.

Heuristic: ceil(characters / 4) — not billed API tokens; good for comparing shapes.

Scenarios (scripted)

Skill pairs (canonical .md → .min.md)

Min-only helpers (signal-core, signal-diff, signal-search) ≈ 1.6K bytes (~389 est. tokens).

Reproduce:

powershell -NoProfile -ExecutionPolicy Bypass -File .\scripts\benchmark.ps1

Architecture

flowchart TB
  subgraph protocol [Protocol layer]
    P["signal.min.md"]
    CORE["signal-core.min.md"]
  end
  subgraph workflow [Workflow skills]
    CKPT["signal-ckpt"]
    GIT["commit / push / pr"]
    REV["signal-review"]
  end
  subgraph context [Context tools]
    DIFF["signal-diff"]
    SRCH["signal-search"]
    ST["signal-state"]
  end
  subgraph persist [Persistence]
    STATE[".signal_state.md"]
  end
  P --> CORE
  P --> CKPT
  P --> GIT
  P --> REV
  P --> DIFF
  P --> SRCH
  ST --> STATE

Tier ladder:

flowchart LR
  S1["/signal — S1"] --> S2["/signal2 — S2"]
  S2 --> S3["/signal3 — S3"]
  S1 -.- D1["~35% vs loose chat"]
  S2 -.- D2["BOOT · aliases · Δ"]
  S3 -.- D3["Auto-CKPT every 5 turns"]

Coding norms (Karpathy-style)

Tiers compress chat. For code edits, the bundle still points at Karpathy-style discipline: small diffs, clear assumptions, verify goals.

Git workflows & CI

CI: .github/workflows/verify.yml runs [scripts/verify.ps1](scripts/verify.ps