StashBase is an open-source, local-first writing workspace that lets people work with Claude Code and Codex while using their own files and previous writing as context. It is for drafting and revising documents with source search, semantic search, and prose-focused review of agent edits. The catalogue lists two instructions associated with the workspace.
Borrowing it
Nothing to install: this file belongs to liliu-z/stashbase. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/liliu-z/stashbase/main/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/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.
<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="Reviewed on agentmods" width="80" 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 | $0.03033 | $0.03033 |
| Opus 5.5 | $0.01213 | $0.01213 |
| Sonnet 5.5 | $0.00607 | $0.00607 |
| Haiku 4.5 | $0.00303 | $0.00303 |
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 10d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on StashBase
Product Context
StashBase is an IDE for writing in ordinary local projects. The main flow is: enter a project → brainstorm with an agent → draft and revise → refine. An empty project is valid; references, search, and wiki building are optional.
- Documents mode is a VSCode-like files/editor workspace.
- Chat mode is a Claude/ChatGPT-like conversation workspace.
- Both share the project and preserve unfinished work. A folder is a project scope and search namespace; the product has no global Library.
Local file handling, preparation, indexing, retrieval, and agent-assisted writing are implemented, including inline prose revision. Existing file diffs and save-conflict comparisons are separate. Defects and missing evidence are not additional planned features.
Search UI says By keyword / By meaning; grep/hybrid are implementation strategies.
Documentation Map
Use this map to find an answer, then the task routes below to choose what to read. These documents are references, not a checklist to read in full for every task.
| Document | Question it answers |
|---|---|
| README.md | What is StashBase, and how do I get started? The short external introduction. |
| Design Docs | What should the product do? Routes to product identity, terminology, vertical journeys, horizontal capabilities, and visual intent. Planned behavior stays in its owning design. |
| Review Guide | How should I scope a review, inspect a change, and report findings? |
| Engineering Boundaries | Which module or process owns a responsibility, and what rules must changes preserve? |
| Journey Coverage | Which code implements a user journey, what evidence exists, and what remains unproven or broken? |
| Release Runbook | How are source CI, packaging, signing, release verification, and publication performed? |
| MAINTENANCE.md | Who maintains each kind of document, when should it change, and how are status and compatibility decisions recorded? |
| CONTRIBUTING.md | How do I set up development and run focused or complete checks? |
| User/operator guides | How does a user or operator use and troubleshoot the product? |
| Release checklists | What still needs checking in the packaged application? |
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.
- 10d ago Changed · +16 lines · +202 tokens per session b5cce2c8dbea
- 18d ago Changed 1fab57021330
- 23d ago Changed · +1 lines · +47 tokens per session 661c6a068ca7
- 25d ago Changed · +1 lines · +11 tokens per session 9cb58d3b3976
- 1mo ago Changed · -9 tokens per session 847221ba9896
- 1mo ago Changed · +19 lines · +267 tokens per session 7bf24ea4e4fb
- 1mo ago Changed · +28 lines · +551 tokens per session 60c1e79cc35f
- 1mo ago Changed · +8 lines · +71 tokens per session d3296f7c04e2
- 2mo 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 (1,273 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,033 tokens to every session, about $0.0121 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 2026-08-30.
stashbase AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stashbase AGENTS.mdliliu-z/stashbase | Instructions file | 1.3k | yesterday | Apache-2.0 | A | 3,033 | 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 | today | 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 |