What is agent-session-parser AGENTS.md?

A set of project instructions for working on a Python library that parses session files from Claude Code, Codex CLI, and Gemini CLI. It defines the project boundaries, documentation to read, shared data format, output formats, and test-first development process.

Use it when modifying session parsing, JSON or Markdown export, batch processing, fixtures, golden files, integration tests, or provider-specific parsers.

It gives coding agents the context needed to make compatible changes without treating the project as a wrapper for an unrelated Go tool or expanding its scope accidentally.

agent-session-parser AGENTS.md — Instructions file by BobDLA

Install

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.

agentmods

npx agentmods add instructions/bobdla/agent-session-parser/agents-md

Clone the repo

git clone --depth 1 https://github.com/BobDLA/agent-session-parser

Made for: Codex, OpenCode.

Per session 645 This file is loaded in full into every session.

When invoked 645 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00645	$0.00645
Opus 5	$0.00322	$0.00322
Sonnet 5	$0.00129	$0.00129
Haiku 4.5	$0.00064	$0.00064

Measured yesterday against content hash ddac912be06d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-session-parser 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 yesterday.

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.

AGENTS.md · 81 lines

What it actually says

AGENTS.md

本文件给进入 session-parser 仓库工作的代理一个最小但明确的上下文。

项目定位

这是一个独立的 Python 库，目标是解析 Claude Code、Codex CLI、Gemini CLI 的会话文件。
当前主线目标是：稳定解析、批量导出、可复用库接口。
不要把当前仓库当成任何现有 Go CLI 的 Python 包装层。

先读这些文档

当前现状与一期边界：docs/PROJECT_STATUS_ZH.md
使用说明：docs/USAGE_ZH.md
监控/状态快照：docs/MONITORING_ZH.md
SessionData contract：docs/SESSION_DATA_CONTRACT_ZH.md
TDD 工作方式：docs/TDD_WORKFLOW_ZH.md
项目约束：docs/PROJECT_CONSTRAINTS_ZH.md
二期 backlog：docs/PHASE2_BACKLOG_ZH.md

当前边界

当前已完成的一期能力：

Claude / Codex / Gemini 的基础解析
统一 SessionData schema
JSON / Markdown emitter
批量导出与对拍脚本
fixture / golden / 集成回归

当前不要主动扩进去的范围：

watcher
ExecAgentAndWatch
provider 安装检测
云同步 / analytics / debug raw 写盘
新 provider 扩展

开发方式

采用 TDD：先加失败测试，再实现，再跑全量测试。
优先使用共享 fixture / golden，而不是只写理想化 mock。
修改解析行为时，优先确认：
- SessionData contract 是否保持稳定
- JSON / Markdown golden 是否需要同步
- 是否需要补 Go / Python 对拍

仓库结构

顶层 API：src/session_parser/api.py
共享 core：src/session_parser/core/
provider 解析器：src/session_parser/providers/
输出器：src/session_parser/emitters/
测试：tests/

补充：

Claude 的 rebuilder 逻辑当前在 src/session_parser/providers/claude/parser.py 的内部辅助函数里。
Codex 当前以单文件会话解析为主。
parse_project(...) 目前只支持 Claude 与 Gemini。

提交前检查

默认执行：

./scripts/check.sh

如果变更涉及参考项目对拍，优先考虑补或运行：

PYTHONPATH=src python scripts/export_reference_compare.py ...

修改原则

优先保持当前公共 API 稳定。
优先保持 fixture / golden 回归稳定。
优先修“结构性差异”和“真实样本差异”，不要先追长尾展示细节。

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.

yesterday First seen · 81 lines · 645 tokens per session scan A ddac912be06d

Subscribe to this mod's changes

agent-session-parser AGENTS.md is an instructions file published in the GitHub repository BobDLA/agent-session-parser (1 stars, last pushed 4mo ago), licensed MIT. It adds 645 tokens to every session, about $0.0032 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.

Data and AI LLM Testing Writing and docs agent claude-code codex-cli gemini-cli python

agent-session-parser AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

AGENTS.md

项目定位

先读这些文档

当前边界

开发方式

仓库结构

提交前检查

修改原则

What this file has done since we first saw it

Other instructions, from other repositories

obsidian-mind CLAUDE.md

obsidian-mind AGENTS.md

parallel-code CLAUDE.md

neo4j-skills AGENTS.md

ox AGENTS.md

open-vibe-island AGENTS.md