Borrowing it
Nothing to install: this file belongs to jiantao88/ai-history. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jiantao88/ai-history/master/AGENTS.mdgit 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/instructions/jiantao88/ai-history/agents-md)<a href="https://agentmods.dev/instructions/jiantao88/ai-history/agents-md"><img src="https://agentmods.dev/badge/instructions/jiantao88/ai-history/agents-md/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/instructions/jiantao88/ai-history/agents-md"><img src="https://agentmods.dev/badge/instructions/jiantao88/ai-history/agents-md.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 | $0.00917 | $0.00917 |
| Opus 5 | $0.00458 | $0.00458 |
| Sonnet 5 | $0.00183 | $0.00183 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
ai-history AGENTS.md 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 9d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
ai-history is a standalone Rust CLI tool that searches and exports AI coding assistant chat history. It reads conversation data from Claude Code, Codex CLI, and Cursor, outputting in Markdown, JSON, Prompt, or Digest format.
Designed to be used inside other AI tool sessions to inject historical context.
Development Commands
cargo build # Debug build
cargo test # Run unit tests
cargo build --release # Release build (LTO + strip)
cargo run -- list # Test with real data
cargo run -- digest <session-id> # Test digest
Architecture
src/
main.rs # CLI dispatch (clap)
cli.rs # Clap derive subcommand definitions
model.rs # Provider-agnostic types: Project, Session, Message, SearchResult
parse.rs # JSONL parsing: mmap + simd-json + memchr line splitting
scoring.rs # BM25 relevance scoring + tokenizer
search.rs # Cross-provider search delegation
digest/
mod.rs # SessionDigest struct, format_digest(), get_or_create_digest()
extractor.rs # Rule-based extraction engine (intent, decisions, code changes, issues)
cache.rs # Disk cache with mtime+size invalidation
llm.rs # Optional Codex API enhancement (--llm flag)
provider/
mod.rs # Provider trait + ProviderRegistry
claude.rs # Claude Code: ~/.claude/projects/ JSONL parser
codex.rs # Codex CLI: ~/.codex/sessions/ rollout JSONL parser
cursor.rs # Cursor: workspaceStorage vscdb SQLite parser
output/
mod.rs # TTY detection
human.rs # Colored terminal output (tables, conversation view)
json.rs # JSON serialization
markdown.rs # Markdown export
prompt.rs # Clean User:/Assistant: prompt format
Key Design Decisions
- Provider trait:
provider/mod.rsdefines theProvidertrait. Each provider implements scan/list/load/search independently. - Flat Message model:
Message.textis pre-flattened from content blocks. Unlike the reference project (Codex-history-viewer) which preserves raw JSON for frontend rendering, this CLI only needs text. - Path decoding: Claude Code encodes project paths with hyphens (
-Users-jack-myapp). Decoded via filesystem-based recursive lookup inclaude.rs::decode_path_with_prefix(). - Codex CLI deduplication: Codex rollout JSONL can duplicate user/assistant messages in both
response_itemandevent_msg. Onlyresponse_itemis used for user/assistant messages. - Cursor vscdb: Cursor stores chat history in SQLite (
state.vscdb) rather than JSONL. Usesrusqliteto querycursorDiskKVtable, JSON-parses bubble arrays from workspace storage. - Pipe detection:
std::io::IsTerminal— TTY gets colored output, pipe gets JSON. - Session Digest: Rule-based extraction (zero-cost, offline) compresses sessions to ~5% of original size. Extracts intent from first user message, decisions from thinking blocks, code changes from tool calls, issues from error patterns. Optional
--llmflag enhances via Anthropic API. Cached to disk with mtime+size invalidation. - Context defaults to digest:
context <id>outputs digest,--fullrestores original full-text behavior. Saves 10-20x tokens while preserving key information.
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.
- 9d ago First seen · 70 lines · 917 tokens per session scan A c9307a274af1
ai-history AGENTS.md is an instructions file published in the GitHub repository jiantao88/ai-history (3 stars, last pushed 2mo ago), licensed MIT. It adds 917 tokens to every session, about $0.0046 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.