agentmods.dev

repo-continuity AGENTS.md

A repository instruction file for Repo Continuity, a system that keeps project knowledge and coding workflows in shared files. It describes the repository layout, collaboration rules, development process, and review requirements.

In plain words
What is it for?
It helps agents understand where files belong, follow the same workflow, hand work between agents, and validate changes before publishing.
Why use it?
It gives coding agents one shared source of project rules instead of relying on chat history or separate tool settings.

Instructions file for CodexOpenCode

5 15d ago A scan 995 tokens original MIT
View the source file vector233/repo-continuity
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/vector233/repo-continuity/agents-md
Clone the repo
git clone --depth 1 https://github.com/vector233/repo-continuity

Made for: Codex, OpenCode.

Per session 995 This file is loaded in full into every session.
When invoked 995 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 $0.00995 $0.00995
Opus 5 $0.00498 $0.00498
Sonnet 5 $0.00199 $0.00199
Haiku 4.5 $0.00100 $0.00100

Measured 2d ago against content hash 67485afdc072, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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 · 66 lines

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.md is the canonical shared instruction file. Codex reads it directly; CLAUDE.md imports 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 Continuity is the product display name. Keep the repo-continuity Skill ID and .repo-continuity-template payload marker stable unless a separately approved compatibility plan changes them. The legacy ai-collaboration-workflow ID 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_REF identical. 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/.

Read the full file on GitHub · 66 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. 2d ago First seen · 66 lines · 995 tokens per session scan A 67485afdc072

Subscribe to this mod's changes

repo-continuity AGENTS.md is an instructions file published in the GitHub repository vector233/repo-continuity (5 stars, last pushed 15d ago), licensed MIT. It adds 995 tokens to every session, about $0.0050 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 2026-08-31.

Project Managementai-agentsai-codingclaude-codecodexdocumentation-template
Related

Other instructions, from other repositories

vibe-log-cli CLAUDE.md

Instructions for vibe-log/vibe-log-cli, covering claude code - vibe-log cli development notes, project architecture overview, key technologies, core directory structure and main components.

vibe-log/vibe-log-cli · 3,738 tokens

mcp-better-vibe-kanban CLAUDE.md

Claude Code instructions for yigitkonur/mcp-better-vibe-kanban, covering claude.md, what this is, build & run, http transport (default port 3000) and environment variables.

yigitkonur/mcp-better-vibe-kanban · 1,452 tokens

jjj AGENTS.md

Instructions for doug/jjj, covering agent instructions, before you write anything, read this first, house rules and verifying changes to this repository.

doug/jjj · 464 tokens

project-os-for-codex AGENTS.md

Instructions for herry2059/project-os-for-codex, covering ai contributor rules, product truth, architecture and security, development workflow and agent integration contract.

herry2059/project-os-for-codex · 656 tokens

AmbyKit CLAUDE.md

Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.

ambystechcom/AmbyKit · 257 tokens

nextjs-skills CLAUDE.md

Instructions for mohamed-hossam1/nextjs-skills: All contribution rules — style, naming, file layout, verification — live in AGENTS.md. Read that first.

mohamed-hossam1/nextjs-skills · 69 tokens