Borrowing it
Nothing to install: this file belongs to shift-editor/shift. 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/shift-editor/shift/main/AGENTS.mdgit clone --depth 1 https://github.com/shift-editor/shiftWrote 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/shift-editor/shift/agents-md)<a href="https://agentmods.dev/instructions/shift-editor/shift/agents-md"><img src="https://agentmods.dev/badge/instructions/shift-editor/shift/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/shift-editor/shift/agents-md"><img src="https://agentmods.dev/badge/instructions/shift-editor/shift/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 | $0.04447 | $0.04447 |
| Opus 5.5 | $0.01779 | $0.01779 |
| Sonnet 5.5 | $0.00889 | $0.00889 |
| Haiku 4.5 | $0.00445 | $0.00445 |
Grade A, and why
shift 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 today.
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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shift Editor - Development Guide
General Guidelines
- Prefer switch statements over long if-else chains when branching on the same value.
- Prefer early returns over nested if-else blocks. Return early for guard clauses to keep the main logic at the top indentation level. In React components, guard on null data at the top (
if (!glyph) return null;) instead of scatteringglyph?.foo ?? fallbackthroughout the JSX. - Prefer
async/awaitwithtry/catchfor asynchronous control flow. - Avoid
.then(...)/.catch(...)chains in application code when the same flow can be written clearly withawait. - Avoid
void promise.catch(...)in React event handlers and normal command handlers. Use anasyncfunction withtry/catchinstead. - Use
void promise.catch(...)only for genuinely fire-and-forget boundaries that cannot be awaited by the caller, such as Electron menu callbacks. Keep those cases local and log or surface the failure. - Name intermediate values. Pull non-trivial expressions (sets, filtered lists, compound conditions) into named
consts or a named function with early returns instead of nesting them inside ternaries, arguments, or JSX. Nested ternaries are a lint error. - Extract repeated logic. When the same condition or mapping appears at several call sites, extract one helper next to the code it belongs to (for example
listSelectionModeinhooks/useListSelection.ts,nudgeMagnitudeintypes/nudge.ts) and use it everywhere. - Avoid async IIFEs assigned into state, for example
state = (async () => { ... })().catch(...). Extract a named helper so the shared-state/memoization code and the async work are readable separately. - Derive lookups over reactive state with
computed(or hold an immutable collection in a signal and replace it). Never hand-maintain a Map/Set that mirrors a signal: a plain collection cannot notify, so readers incomputed/effects go stale.shift/no-mutable-collection-fieldenforces this; annotate a genuinely non-reactive field with// non-reactive: <reason>. - Do not prefix commit messages or pull request titles with
[codex].
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.
- today Changed · +1 lines · +121 tokens per session 756a7ffec2bd
- yesterday Changed · +2 lines · +100 tokens per session f1a7a5623730
- 3d ago Changed · +13 tokens per session 063bb4f0d589
- 5d ago Changed · +18 tokens per session a02d0848bbb3
- 7d ago Changed · +3 lines · +121 tokens per session f1c1aa3ceda1
- 11d ago Changed · +9 lines · +437 tokens per session 82dc6cbe74ec
- 17d ago Changed · +1 lines · +16 tokens per session 77e3b68aaba7
- 21d ago Changed · +16 tokens per session acf8490f2024
- 29d ago Changed · +1 lines · +106 tokens per session 5bfe3250f625
- 1mo ago First seen · 211 lines · 3,499 tokens per session scan A e4aca88e0f3a
shift AGENTS.md is an instructions file published in the GitHub repository shift-editor/shift (379 stars, last pushed today), licensed Apache-2.0. It adds 4,447 tokens to every session, about $0.0178 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 2026-09-01.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.