signal-history-search

signal-history-search is a skill for Claude Code, Codex from NicolaiSchmid/agent-skills. It costs 28 tokens per session (1,111 once invoked), scanned A, original, MIT.

A macOS search tool for Signal Desktop, the computer app for Signal messages, that queries its local encrypted message database.

In plain words
What is it for?
It helps list chats, search messages by phrase or regular expression, filter by person or date, and show nearby messages for context.
Why use it?
It finds past conversations quickly without exporting them or opening Signal Desktop.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps list chats, search messages by phrase or regular expression, filter by person or date, and show nearby messages for context.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nicolaischmid/agent-skills/signal-history-search
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.

Any agent
npx skills add NicolaiSchmid/agent-skills --skill signal-history-search
Clone the repo
git clone --depth 1 https://github.com/NicolaiSchmid/agent-skills

Made for: Claude Code, Codex.

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-history-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/nicolaischmid/agent-skills/signal-history-search/github.svg)](https://agentmods.dev/skills/nicolaischmid/agent-skills/signal-history-search)
Your own site
<a href="https://agentmods.dev/skills/nicolaischmid/agent-skills/signal-history-search"><img src="https://agentmods.dev/badge/skills/nicolaischmid/agent-skills/signal-history-search/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for signal-history-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/nicolaischmid/agent-skills/signal-history-search"><img src="https://agentmods.dev/badge/skills/nicolaischmid/agent-skills/signal-history-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,111 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00028 $0.01111
Opus 5 $0.00014 $0.00556
Sonnet 5 $0.00006 $0.00222
Haiku 4.5 $0.00003 $0.00111

Measured 12d ago against content hash 983902364d6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

signal-history-search 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 12d 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.

skills/signal-history-search/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Direct SQL search against Signal Desktop's encrypted database. Queries complete in under 1 second against live data.

When to use

  • You need to quote or summarize prior Signal conversations.
  • You already have Signal Desktop installed on macOS.
  • You want fast, instant search without export delays.

How it works

  1. Retrieves the encryption key from macOS Keychain (Signal Safe Storage)
  2. Decrypts the key using PBKDF2 (same as Signal Desktop)
  3. Opens the SQLite database directly with SQLCipher
  4. Runs SQL queries against messages and conversations tables
  5. No files are written; searches happen in memory

First run caches the Python environment path (~5-10s setup), subsequent runs are sub-second.

Usage

# List all available chats
signal-search list

# Dump all messages from a specific day
signal-search dump --date "2026-01-25"

# Dump a specific day's chat with one person
signal-search dump --date "2026-01-25" --chat "Dariush"

# Search within a specific chat
signal-search search --query "istanbul" --chat "Monika"

# Search with context (messages before/after matches)
signal-search search --query "flight" --chat "Monika" --context 3

# Regex search across all chats
signal-search search --query "invoice.*\d{4}"

# Literal string search (not regex)
signal-search search --query "100$" --literal

# Case-sensitive search
signal-search search --query "API" --case-sensitive

# Limit number of results
signal-search search --query "meeting" --max-count 10

Commands

Command Description
list List all available chats (name and type)
dump Dump all messages from a specific day
search Search messages

Dump Flags

Flag Short Description
--date <YYYY-MM-DD> -d Date to dump (required)
--chat <name> -c Filter to chats containing this string

Search Flags

Flag Short Description
--query <pattern> -q Search pattern (regex by default)
--chat <name> -c Filter to chats containing this string
--context <n> -C Show N messages before and after matches
--max-count <n> -m Stop after N matches
--case-sensitive -s Case-sensitive search (default: smart-case)
--literal -F Treat query as literal string, not regex

Read the full file on GitHub · 134 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 134 lines · 28 tokens per session scan A 983902364d6b

Subscribe to this mod's changes

signal-history-search is a skill published in the GitHub repository NicolaiSchmid/agent-skills (2 stars, last pushed 7mo ago), licensed MIT. It adds 28 tokens to every session and 1,111 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.

Related

Other skills, from other repositories