Borrowing it
Nothing to install: this file belongs to vector233/repo-continuity. 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/vector233/repo-continuity/main/AGENTS.mdgit clone --depth 1 https://github.com/vector233/repo-continuityWrote 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/vector233/repo-continuity/agents-md)<a href="https://agentmods.dev/instructions/vector233/repo-continuity/agents-md"><img src="https://agentmods.dev/badge/instructions/vector233/repo-continuity/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/vector233/repo-continuity/agents-md"><img src="https://agentmods.dev/badge/instructions/vector233/repo-continuity/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 | $0.00995 | $0.00995 |
| Opus 5.5 | $0.00398 | $0.00398 |
| Sonnet 5.5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
repo-continuity 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 1mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
This repository develops and distributes Repo Continuity. The core product knowledge-base payload lives under template/; opt-in vendor overlays live under adapters/. This maintenance repository intentionally does not keep a second root zettelkasten/.
Repository Structure
template/: canonical files copied into downstream projects.adapters/: canonical opt-in Codex and Claude Code model-routing overlays.skills/repo-continuity/: companion Agent Skill and bootstrap tooling.scripts/validate_distribution.py: end-to-end distribution contract.docs/: maintainer and publishing documentation.examples/: fictional initialized-project walkthroughs.
Cross-Agent Collaboration Contract
AGENTS.mdis the canonical shared instruction file. Codex reads it directly;CLAUDE.mdimports it for Claude Code.- Shared behavior belongs in repository files, not chat history, vendor memory, or tool-local state.
- Vendor-specific files are adapters only. Keep requirements, workflow semantics, validation, and handoff rules vendor-neutral.
Repo Continuityis the product display name. Keep therepo-continuitySkill ID and.repo-continuity-templatepayload marker stable unless a separately approved compatibility plan changes them. The legacyai-collaboration-workflowID and marker may appear only in explicit migration guidance or compatibility checks.- Keep the Quick Start release tag, payload baseline, distribution validator version, and Companion Skill
DEFAULT_REFidentical. Never describe an installation as pinned while its bootstrap defaults to a moving branch. - The downstream core must remain usable with Markdown and Git alone. Companion-Skill scripts are optional automation and must not be copied into or required by
template/. - Optional vendor adapters must stay outside
template/, require explicit installation opt-in, and preserve the user's root-session model unless a separately approved profile says otherwise. - Downstream workflow feedback is opt-in, evidence-backed, sanitized, and user-approved before publication. Never add telemetry or automatic cross-project collection.
- Large requirements use bounded decomposition: prefer an external Epic, Issue, or Milestone; otherwise allow one thin local Initiative above independent child WORK records. Preserve one stable WORK per branch-bound delivery, forbid recursive Initiative or parent-WORK trees, and keep child status and validation authoritative in each WORK.
- When workflow behavior changes, align the canonical payload, Skill, documentation, examples, and validation as applicable.
- Never put repository-specific release, publishing, or maintenance material in
template/.
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.
- 1mo ago First seen · 66 lines · 995 tokens per session scan A 67485afdc072
repo-continuity AGENTS.md is an instructions file published in the GitHub repository vector233/repo-continuity (5 stars, last pushed 1mo ago), licensed MIT. It adds 995 tokens to every session, about $0.0040 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.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.