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.
npx skills add NicolaiSchmid/agent-skills --skill signal-history-searchgit clone --depth 1 https://github.com/NicolaiSchmid/agent-skillsWrote 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.
[](https://agentmods.dev/skills/nicolaischmid/agent-skills/signal-history-search)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
Signal History Search
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
- Retrieves the encryption key from macOS Keychain (
Signal Safe Storage) - Decrypts the key using PBKDF2 (same as Signal Desktop)
- Opens the SQLite database directly with SQLCipher
- Runs SQL queries against
messagesandconversationstables - 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 |
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.
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.
- 12d ago First seen · 134 lines · 28 tokens per session scan A 983902364d6b
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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.