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 jiantao88/ai-history --skill claudegit clone --depth 1 https://github.com/jiantao88/ai-historyWrote 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/jiantao88/ai-history/claude)<a href="https://agentmods.dev/skills/jiantao88/ai-history/claude"><img src="https://agentmods.dev/badge/skills/jiantao88/ai-history/claude/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/jiantao88/ai-history/claude"><img src="https://agentmods.dev/badge/skills/jiantao88/ai-history/claude.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 | $0.00052 | $0.00939 |
| Opus 5 | $0.00026 | $0.00469 |
| Sonnet 5 | $0.00010 | $0.00188 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade C, and why
ai-history scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
git clone https://github.com/jiantao88/ai-history.git /tmp/ai-history && /tmp/ai-history/setup && rm -rf /tmp/ai-history How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
This skill provides access to AI coding assistant chat history across multiple providers
(Claude Code, Codex CLI, Cursor). It uses the ai-history CLI tool installed at ~/.cargo/bin/ai-history.
Prerequisites
The ai-history binary must be installed. If not found, guide the user:
Run this to install:
git clone https://github.com/jiantao88/ai-history.git /tmp/ai-history && /tmp/ai-history/setup && rm -rf /tmp/ai-history
Commands
/ai-history or /ai-history list
List all projects that have chat history.
~/.cargo/bin/ai-history list --json 2>/dev/null
Parse the JSON output and present as a readable table.
/ai-history sessions <project>
List sessions for a project. The <project> argument supports fuzzy matching (substring).
~/.cargo/bin/ai-history sessions "<project>" --json 2>/dev/null
/ai-history show <session-id>
Show messages from a specific session. Session ID can be abbreviated (first 8+ chars).
~/.cargo/bin/ai-history show "<session-id>" --compact --json 2>/dev/null
/ai-history search <query>
Search across all chat history for a keyword or phrase.
~/.cargo/bin/ai-history search "<query>" --limit 10 --json 2>/dev/null
/ai-history context <session-id>
Load a past session as structured context (digest format — compressed summary of intent, decisions, code changes, and conclusions). This is the recommended way to inject history.
~/.cargo/bin/ai-history context "<session-id>" 2>/dev/null
After fetching:
- Read and understand the digest
- Present a brief summary:
CONTEXT LOADED (Digest) ════════════════════════════════════════ Session: <summary> Provider: <provider> Project: <project> Date: <date> ════════════════════════════════════════ - Tell the user you now have the context and can continue the work.
For full uncompressed conversation (when digest isn't enough):
~/.cargo/bin/ai-history context "<session-id>" --full 2>/dev/null
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 · 129 lines · 52 tokens per session scan C 69567cae7994
ai-history is a skill published in the GitHub repository jiantao88/ai-history (3 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 939 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
chat-history
Search, inspect, and export Claude Code, Cursor, and Codex conversation history. Use when the user asks about past conversations, wants to find a previous session, needs to search chat history, wants a summary of what they worked on, or asks to resume a session. Also use when the user says "what did I work on", "find…
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent graph-based memory. Recall context before responding, remember insights after. Each group has private memory; global memory is read-only.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory for MiniMax Code. Recall durable context, store important facts and decisions, and link related memories with the mnemon CLI.