What is taskcenter AGENTS.md?

Project instructions for TaskCenter, a local tool for managing coding tasks and their acceptance. They define privacy rules, required task registration, and checks to run before completion.

Guiding agents working on TaskCenter, including task registration, safe file access, and running synchronization, linting, tests, and diff checks.

They prevent session data and credentials from being exposed and ensure claimed work is checked before it is accepted.

How xiaogezi/taskcenter configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to xiaogezi/taskcenter. 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/xiaogezi/taskcenter/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/xiaogezi/taskcenter

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/xiaogezi/taskcenter/agents-md/github.svg)](https://agentmods.dev/instructions/xiaogezi/taskcenter/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/xiaogezi/taskcenter/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaogezi/taskcenter/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/xiaogezi/taskcenter/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaogezi/taskcenter/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,897 This file is loaded in full into every session.

When invoked 1,897 The same file — it is already loaded in full.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5.1	$0.01897	$0.01897
Opus 5.5	$0.00759	$0.00759
Sonnet 5.5	$0.00379	$0.00379
Haiku 4.5	$0.00190	$0.00190

Measured 21d ago against content hash 9fa3f413f2bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

taskcenter 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 21d 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.

AGENTS.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TaskCenter Agent Rules

底层原则：任务即契约

任务即契约：以契约约束执行，以持久状态管理过程，以证据判定完成。

所有后续改动必须符合这一原则；新增能力应说明其如何服务契约、过程状态或交付证据，不能削弱已有约束。

契约约束执行：明确目标、范围、授权与验收条件。执行方法可在契约内调整；扩大范围、改变目标或降低验收标准必须形成显式契约变更，不得静默修改。
持久状态管理过程：任务事实、进展、阻塞与恢复依据必须可持久化、可追溯，不能仅依赖聊天或进程内状态。结果未知时先核对已有事实，再决定恢复或重试，避免重复副作用。
证据判定完成：完成结论依据验收条件及绑定当前工作对象、契约和产物版本的证据；Agent 声明、命令已发出或单项测试通过不能替代独立验收。验证强度与风险相称，未验证项如实记录。

PCA 提供版本化规格与项目知识；TaskCenter 管理本次委托的契约、生命周期与交付证据，最终验收由独立授权主体完成。模型选择、派发、工具执行、重试与终止仍归宿主和当前主模型；该原则不恢复已退役的编排能力，也不增加自动 Review 门禁。

Safety boundaries

TaskCenter is a local-only task governance tool. Do not add remote upload of session content without a separate privacy and authentication design.
Read Codex session data only from ~/.codex/sessions/**/*.jsonl and ~/.codex/session_index.jsonl.
Never read ~/.codex/auth.json, API keys, cookies, or other credentials.
Never modify files under ~/.codex; user-owned integration config changes require explicit user action.
- 唯一例外：格子已批准 instory-pca-2 的单个 automations/instory-pca-2/memory.md 通过 apply_patch 新建/更新。必须由 config/automation-memory.json 的启用绑定、本机宿主 automation Session 元数据、启动消息和登记工作区共同验证，补丁与落盘均须通过结构/路径/成功基线校验并留审计；不得修改其他 ~/.codex 文件或配置，不授予 inStory 仓库写入。
Treat an assistant's done_claimed status as an implementation claim, not acceptance.

Required workflow

One registered Codex Session may carry multiple formal tasks sequentially. A new task may be created after the previous task is no longer planned, in_progress, or blocked; only one formal task may be active in a Session at a time. Reuse the existing task for the same deliverable, and create a distinct task for a new deliverable without requiring a new Session.

Before changing project files in an MCP-enabled session:

Prefer taskcenter_task_begin to register the real Session and create the task in one call. Existing clients may call taskcenter_session_register followed by taskcenter_task_create.
Supply a v2 contract with goal, scope, non-goals, plan, structured acceptance criteria, workflow profile, review policy, optional execution environment, and a verification plan for standard / strict work.
Continue only after accepted=true and a distinct task_id are returned.

Read the full file on GitHub · 74 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.

21d ago Changed · +1 lines · -390 tokens per session 9fa3f413f2bf
1mo ago Changed · +12 lines · +776 tokens per session 930c9eeedf70
1mo ago Changed · +32 lines · +1,263 tokens per session f3162f0d0d83
2mo ago First seen · 29 lines · 248 tokens per session scan A 8ae8121c7eb8

Subscribe to this mod's changes

taskcenter AGENTS.md is an instructions file published in the GitHub repository xiaogezi/taskcenter (0 stars, last pushed 22d ago), licensed Apache-2.0. It adds 1,897 tokens to every session, about $0.0076 per session on Opus 5.5. 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.

Project management

taskcenter AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
taskcenter AGENTS.mdxiaogezi/taskcenter	Instructions file	0	22d ago	Apache-2.0	A	1,897	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

taskcenter: Instructions file for Codex