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/liliu-z/stashbase/agents-mdgit clone --depth 1 https://github.com/liliu-z/stashbaseWrote 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/liliu-z/stashbase/agents-md)<a href="https://agentmods.dev/instructions/liliu-z/stashbase/agents-md"><img src="https://agentmods.dev/badge/instructions/liliu-z/stashbase/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 5.1 | $0.01893 | $0.01893 |
| Opus 5 | $0.00946 | $0.00946 |
| Sonnet 5 | $0.00379 | $0.00379 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade A, and why
stashbase 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 6d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent maintenance contract for this repo
The human/AI operating model is MAINTENANCE.md. Follow it
for design, implementation, review, and evidence ownership.
Before writing code, consult the affected product area in design-docs/ and
the owning engineering contract in code-review/. For code review, pin the
diff and follow the diff-first route in code-review/README.md, then use
code-review/journey-coverage.md to recover product intent and evidence.
Product docs define intent and observable behavior; review contracts define
risky Interfaces, invariants, implementation entry points, and validation.
Code remains the source of truth for the current implementation.
Keep the affected docs current in the same change as code. This is not a later documentation pass. All committed docs are English-only.
GitHub access for this repository
For GitHub write operations on liliu-z/stashbase (including PR/issue
comments, reviews, merges, and workflow dispatches), use the locally
authenticated gh CLI directly. The GitHub Connector is authenticated as a
different account and does not have write access to this repository, so do not
probe a Connector write first. Connector reads remain available when useful.
Temporary worktrees
Secondary Git worktrees do not inherit ignored local dependencies. Before
running Electron E2E journeys that exercise indexing or sync, make sure the
worktree has python/.venv.nosync: reuse a working primary checkout's venv via
an explicit symlink when appropriate, or run pnpm setup:python. Without it,
/api/index-status and /api/sync return misleading 500 responses with
ModuleNotFoundError: No module named 'mfs'; treat that as worktree setup, not
as a product regression. Never commit the venv or its symlink.
Electron launch environment
The agent host may inherit ELECTRON_RUN_AS_NODE=1. Remove it from the child
environment before any command that must launch Electron as a desktop runtime,
including Electron smoke tests, Electron E2E, and temporary visual harnesses.
On POSIX, run commands as
env -u ELECTRON_RUN_AS_NODE pnpm test:electron:smoke (and apply the same
prefix to the other Electron launch command). If require('electron').app is
undefined or a smoke fails at app.setPath, treat the inherited variable as
environment setup, not a product regression. Do not remove the variable from
flows that intentionally run Electron's embedded Node runtime.
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.
- 6d ago First seen · 160 lines · 1,893 tokens per session scan A 4b79c2f8baf0
stashbase AGENTS.md is an instructions file published in the GitHub repository liliu-z/stashbase (548 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,893 tokens to every session, about $0.0095 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.
Other instructions, from other repositories
siyuan AGENTS.md
AGENTS.md instructions for siyuan-note/siyuan, covering agents.md, 1. non-negotiable constraints, do not hand-edit, verification and prohibited operations and 2. project-specific rules.
chat-on-steroids CLAUDE.md
Claude Code instructions for totec448-spec/chat-on-steroids: Read and follow AGENTS.md before changing this repository.
Starcat AGENTS.md
AGENTS.md instructions for starcat-app/Starcat, covering agents.md, 🚨 硬性铁律（每次写代码前必读，违反即返工）, 🌿 git 分支与 worktree（强制）, 🧭 主进度索引（每次开工前必读） and 状态符号（与功能实现总览.md 同步）.
tandem-browser CLAUDE.md
Claude Code instructions for hydro13/tandem-browser: Read AGENTS.md in full — it is the development guide for coding agents working on this repository: workflow, testing gates, git discipline, context discipline, and the anti-detection architecture rules that must never be violated.
llm-wiki-newsroom AGENTS.md
AGENTS.md instructions for alfadur7/llm-wiki-newsroom, covering llm wiki newsroom — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
llm-wiki-newsroom GEMINI.md
Gemini CLI instructions for alfadur7/llm-wiki-newsroom, covering llm wiki newsroom — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.