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 agentmods add instructions/xiaojiou176-open/agent-export/agents-mdgit clone --depth 1 https://github.com/xiaojiou176-open/agent-exportWrote 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/xiaojiou176-open/agent-export/agents-md)<a href="https://agentmods.dev/instructions/xiaojiou176-open/agent-export/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaojiou176-open/agent-export/agents-md.svg" alt="Measured on agentmods" 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 | $0.02406 | $0.02406 |
| Opus 5 | $0.01203 | $0.01203 |
| Sonnet 5 | $0.00481 | $0.00481 |
| Haiku 4.5 | $0.00241 | $0.00241 |
Grade A, and why
agent-export 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 4d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentExport Agent Guide
Repo Summary
AgentExport 是一个 local-first archive and governance workbench for AI agent transcripts。
Product Kernel：本地优先地导出、归档、检索 transcript 与 evidence，并把治理决策收进 repo-owned workbenchPrimary Surface：CLI-firstSecondary Surface 1：local archive shell / reports shellSecondary Surface 2：repo-owned integration packSecondary Surface 3：read-only governance MCP bridgeFlagship Public Packet：GitHub repo + CLI quickstart + archive shell proofFront Door Today：先讲 CLI quickstart，再讲 archive shell proof；integration pack 和 governance MCP 仍然按 secondary surfaces 记账，不抢主门- 当前阶段：Codex dual-source + Claude Code minimal connector + shared JSON/HTML export + archive index + local metadata search + semantic retrieval + persistent local semantic index + hybrid retrieval + local multi-agent archive shell + local retrieval report artifacts + workspace-local transcript backlinks + local reports shell + reports-shell metadata search + minimal stdio MCP bridge + repo-owned integration materializer/doctor + drift-aware integration doctor hardening + platform-aware integration doctor diagnostics + integration pack-shape hardening + integration onboarding experience + integration evidence pack + integration evidence shell search + machine-readable integration evidence + integration evidence timeline/diff + evidence gate / explain + baseline registry + policy packs + promotion engine/history + remediation bundle studio + read-only governance MCP surface + current-decision automation + repo-local governance workbench capability 已吸收进当前产品真相；Wave 1 front door 仍以 CLI-first 解释，默认 Codex 主路径仍是 app-server
Core Rules
-
文档先于代码
- 行为语义、边界、状态语义，先写进
docs/，再写实现。
- 行为语义、边界、状态语义，先写进
-
先守住上游真理源
- 当前完整导出的主真源，先按 CodexMonitor 的
thread/readcontract 理解。 - 官方 Codex 源码决定 thread/source 真相层，不要凭印象猜。
- 当前完整导出的主真源，先按 CodexMonitor 的
-
source / core / output 分层
connectors/：负责取数core/：负责 transcript / archive contractoutput/：负责 Markdown / JSON / HTML
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.
- 4d ago First seen · 189 lines · 2,406 tokens per session scan A edcec73c04a3
agent-export AGENTS.md is an instructions file published in the GitHub repository xiaojiou176-open/agent-export (1 stars, last pushed 1mo ago), licensed MIT. It adds 2,406 tokens to every session, about $0.0120 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
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).