a5sql-mcp: Skill for Claude Code

.agents/skills/ctx-agent-history-search/SKILL.md

ctx-agent-history-search is a skill for Claude Code, Codex from takuyaw-w/a5sql-mcp. It costs 34 tokens per session (1,751 once invoked), scanned C, original, MIT.

A local search tool for finding relevant information in earlier coding-agent sessions, such as decisions, attempts, and transcripts.

In plain words
What is it for?
Use it to search past sessions for commands, timelines, user intent, failures, and source references. It can also research a historical topic across those sessions.
Why use it?
It helps recover useful context before starting work, so you do not repeat failed approaches or miss earlier decisions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is takuyaw-w/a5sql-mcp's own configuration. It tells Claude Code and Codex how to work on a5sql-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything a5sql-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to takuyaw-w/a5sql-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/takuyaw-w/a5sql-mcp/main/.agents/skills/ctx-agent-history-search/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/takuyaw-w/a5sql-mcp

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 ctx-agent-history-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/takuyaw-w/a5sql-mcp/ctx-agent-history-search/github.svg)](https://agentmods.dev/skills/takuyaw-w/a5sql-mcp/ctx-agent-history-search)
Your own site
<a href="https://agentmods.dev/skills/takuyaw-w/a5sql-mcp/ctx-agent-history-search"><img src="https://agentmods.dev/badge/skills/takuyaw-w/a5sql-mcp/ctx-agent-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 ctx-agent-history-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/takuyaw-w/a5sql-mcp/ctx-agent-history-search"><img src="https://agentmods.dev/badge/skills/takuyaw-w/a5sql-mcp/ctx-agent-history-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,751 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00034 $0.01751
Opus 5 $0.00017 $0.00875
Sonnet 5 $0.00007 $0.00350
Haiku 4.5 $0.00003 $0.00175

Measured 11d ago against content hash b374433f7b64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

ctx-agent-history-search scanned grade C with 2 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 11d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://ctx.rs/install | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://ctx.rs/install | sh
.agents/skills/ctx-agent-history-search/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use ctx whenever you need to reference previous coding-agent sessions. Those transcripts can contain user intent, decisions, previous work timelines, past attempts, and what worked or failed.

Use this skill in two modes:

  • retrieval before work, when prior sessions may contain decisions, commands, failures, or source citations that affect the current task;
  • history research reports, when the user asks an agent or read-only subagent to research a historical topic across prior local agent sessions.

Prerequisites

  • Require the ctx CLI to be installed and set up. If it is missing and installing tools is appropriate for the task, install it with:

    curl -fsSL https://ctx.rs/install | sh
    
  • First setup can take time while ctx indexes past sessions. If needed, keep it running in the background or in tmux, or wait for it to finish.

  • If ctx remains unavailable, say local history search is unavailable and do not invent results.

Workflow

  1. Confirm ctx is ready when starting from a cold context:

    ctx status
    ctx sources
    

    Use ctx status --json or ctx sources --json only when a script needs exact fields.

  2. Search with normal language first. Add terms or filters when useful:

    ctx search "<query>"
    ctx search "<query>" --refresh off
    ctx search "<query>" --provider codex
    ctx search "<query>" --workspace <workspace>
    ctx search "<query>" --file <path>
    ctx search "<query>" --since 30d
    ctx search "<query>" --term "<related term>" --term "<error text>"
    ctx search "<query>" --session <ctx-session-id>
    ctx search "<query>" --verbose
    

    Use default text output for agent reading. Do not add --json for search, show, or locate unless you are piping it into jq or a script, or you need exact machine-readable fields. JSON output is much larger and can quickly consume the context window.

    When the prompt asks for a topic history or report across multiple sessions, run several ctx search queries with different wording and filters to find promising sessions. Use scoped ctx search "<query>" --session <ctx-session-id> when a session looks relevant and you need dense event-level matches from that session.

Read the full file on GitHub · 206 lines

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. 11d ago First seen · 206 lines · 34 tokens per session scan C b374433f7b64

Subscribe to this mod's changes

ctx-agent-history-search is a skill published in the GitHub repository takuyaw-w/a5sql-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 1,751 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

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…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens