WEIPING_LAB AGENTS.md

A set of project-specific instructions for WEIPING_LAB, a research workbench for discovering ideas, planning experiments, writing from evidence, and supporting audits.

In plain words
What is it for?
Use it when implementing, maintaining, releasing, monitoring, or upgrading the project. It identifies the files and project rules that must be checked first.
Why use it?
It sets boundaries for reliable research work, including avoiding invented experiments, results, citations, and secret values.

Instructions file for CodexOpenCode

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/appleweiping/weiping_lab/agents-md
Clone the repo
git clone --depth 1 https://github.com/appleweiping/WEIPING_LAB

Made for: Codex, OpenCode.

Per session 712 This file is loaded in full into every session.
When invoked 712 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.

ModelPer sessionOnce invoked
Fable 5 $0.00712 $0.00712
Opus 5 $0.00356 $0.00356
Sonnet 5 $0.00142 $0.00142
Haiku 4.5 $0.00071 $0.00071

Measured 3d ago against content hash 462568088844, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

WEIPING_LAB 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 3d 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 · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WEIPING_LAB Agent Instructions

WEIPING_LAB is an honest research workbench for phenomenon-driven discovery, kill-first ideation, experiment planning, evidence-gated writing, and audit support.

Source Of Truth

Read AGENTS.md, README.md, CLAUDE.md, pyproject.toml, lab/runtime.py, lab/core/config.py, and .codex/skills/weiping-lab/SKILL.md before non-trivial work. The project skill is mandatory for implementation, release, maintenance, monitoring, or upgrade tasks.

Boundaries

  • Do not fabricate experiments, paper results, baselines, or citations.
  • Do not treat bridge scaffolds as completed experiments.
  • Keep config environment-driven; never add real keys, private endpoints, account names, or secret-shaped placeholders to tracked source.
  • Keep lab/workspace/ source tracked, but generated root workspace/ content stays local/ignored.
  • Use agentmemory through AGENTMEMORY_URL for active memory; local outbox fallback must be redacted.
  • Preserve legacy VIPIN_LAB_* compatibility only as explicit fallbacks; new docs and variables should use WEIPING_LAB_*.
  • Treat experiments/results/*.json as untrusted input. Preserve the v1.0 result contract, deterministic evidence classification, source digests, and claim-to-block links; an LLM or producer-supplied label must never promote evidence.

WEIPING Constellation

WEIPING_WIKI is the public durable route map, not a runtime dependency. WEIPING_COUNCIL is the companion deliberation/review layer. Lab may consume council session artifacts, but it must not require council private state, local DBs, caches, .env, or active server processes to run its own verification.

Recurring WEIPING maintenance may inspect entry evidence, status commands, docs, and git state. It should not edit lab code, workspace outputs, datasets, experiment results, or generated artifacts unless the user explicitly scopes lab work.

Artifact handoffs are path-and-schema contracts, not shared runtime state. The main handoff files are workspace/*/session.json, workspace/ideas/<idea_id>/idea.json, plan.json, paper.json, EXPERIMENT_PLAN.md, EXPERIMENT_TRACKER.md, experiments/results/*.json, and redacted agentmemory-outbox.jsonl. The result schema is documented in docs/RESULT_CONTRACT.md; bridge-generated workspaces include a plan-specific copy and example.

Read the full file on GitHub · 49 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.

  1. 3d ago First seen · 49 lines · 712 tokens per session scan A 462568088844

Subscribe to this mod's changes

WEIPING_LAB AGENTS.md is an instructions file published in the GitHub repository appleweiping/WEIPING_LAB (120 stars, last pushed 5d ago), licensed MIT. It adds 712 tokens to every session, about $0.0036 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 2026-08-30.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens