relaycore CLAUDE.md

relaycore CLAUDE.md is an instructions file for coding agents from totooss/relaycore. It costs 634 tokens per session, scanned A, original, MIT.

Repository instructions that require RelayCore, a durable project-memory service, to store decisions, rules, lessons, and important task results.

In plain words
What is it for?
Loading relevant memory before work, syncing rule files, recording durable outcomes, and committing task context for future sessions.
Why use it?
They prevent important project context from being lost when a coding session or runtime ends.

Instructions file

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/totooss/relaycore/claude-md
Clone the repo
git clone --depth 1 https://github.com/totooss/relaycore

Wrote 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.

agentmods badge for relaycore CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/totooss/relaycore/claude-md.svg)](https://agentmods.dev/instructions/totooss/relaycore/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/totooss/relaycore/claude-md"><img src="https://agentmods.dev/badge/instructions/totooss/relaycore/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 634 This file is loaded in full into every session.
When invoked 634 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 $0.00634 $0.00634
Opus 5 $0.00317 $0.00317
Sonnet 5 $0.00127 $0.00127
Haiku 4.5 $0.00063 $0.00063

Measured 3d ago against content hash 547c1be05e6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

relaycore CLAUDE.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 3d 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.

CLAUDE.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RelayCore Runtime Contract For Claude

Claude should use RelayCore as the durable memory backend for this repository.

RULES.md is the versioned editorial source for durable methodology and runtime rules. Sync it into RelayCore with relaycore sync-rules --rules-file RULES.md whenever the file changes.

Hard Rules

  • Native Claude memory is not the project memory system.
  • Do not assume built-in memory will be available in future sessions.
  • Do not treat prior chat recall as an acceptable substitute for RelayCore.
  • Any project decision that should survive the current session must be written to RelayCore.

Minimum Task Sequence

  1. memory_auto_prepare
  2. if unavailable, fall back to memory_begin_task and memory_context
  3. short preflight describing the loaded relevant rules, decisions, lessons, and rejected paths
  4. work
  5. memory_add or memory_propose for durable outcomes
  6. memory_commit_task

What Must Go To RelayCore

  • accepted decisions
  • rejected options and reasons
  • reusable rules
  • lessons learned
  • task progress that another runtime may need
  • artifact references that matter later

What Does Not Need Durable Storage

  • ephemeral chain-of-thought
  • transient drafting text
  • one-off exploration that does not affect future work
  • formatting chatter that has no project value

Retrieval Guidance

  • Prefer memory_context with a bounded token budget.
  • Prefer memory_auto_prepare for startup bootstrap and memory_context for bounded follow-up retrieval.
  • Prefer compact summaries over dumping full historical transcripts.
  • Read active decisions, rules, lessons, and relevant rejected knowledge before making new decisions.
  • If RULES.md changes, sync it into RelayCore before considering the rule change complete.
  • If the task involves planning, design, implementation, automation, or refactoring, preflight should explicitly verify whether the external-reference baseline rule applies.

Mission Control Boundary

  • Treat Mission Control command publishing as a manual operator override path.
  • Default to agent-driven command publication during normal runtime collaboration.
  • Use the web UI command form only for fallback dispatch, debugging, or session seeding.

Read the full file on GitHub · 69 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. 3d ago First seen · 69 lines · 634 tokens per session scan A 547c1be05e6e

Subscribe to this mod's changes

relaycore CLAUDE.md is an instructions file published in the GitHub repository totooss/relaycore (1 stars, last pushed 1mo ago), licensed MIT. It adds 634 tokens to every session, about $0.0032 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.