titen AGENTS.md

titen AGENTS.md is an instructions file for Codex, OpenCode from RamaAditya49/titen. It costs 968 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Titen, a collaborative memory service for AI agents that can run on Cloudflare or Bun. It describes its shared TypeScript core, database adapters, evidence-based context, and optional model-assisted enrichment.

In plain words
What is it for?
Use it when working on Titen's memory service, architecture, APIs, deployment adapters, runtime compatibility, or durable enrichment pipeline.
Why use it?
It tells agents which documents and current implementation rules to trust when planning or changing a system with multiple runtimes and deployment targets.

Instructions file for CodexOpenCode

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/ramaaditya49/titen/agents-md
Clone the repo
git clone --depth 1 https://github.com/RamaAditya49/titen

Made for: Codex, OpenCode.

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 titen AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ramaaditya49/titen/agents-md.svg)](https://agentmods.dev/instructions/ramaaditya49/titen/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ramaaditya49/titen/agents-md"><img src="https://agentmods.dev/badge/instructions/ramaaditya49/titen/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 968 This file is loaded in full into every session.
When invoked 968 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 $0.00968 $0.00968
Opus 5 $0.00484 $0.00484
Sonnet 5 $0.00194 $0.00194
Haiku 4.5 $0.00097 $0.00097

Measured 5d ago against content hash c666c6227d23, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

titen 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 5d 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 · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for coding agents working in the Titen repository.

Product

Titen is a Level 6 collaborative memory fabric built on a Level 5 evidence-grounded context kernel. It supports personal, company, and enterprise agent memory on Cloudflare or a Bun/VPS deployment.

Read in this order:

  1. docs/PRD.md — product contract;
  2. docs/architecture/overview.md — component boundaries;
  3. relevant file under docs/architecture/, docs/reference/, or docs/deployment/;
  4. blueprint.md only for research evidence and platform history.

When documents disagree, direct user instructions and verified current behavior win, then PRD, accepted ADRs, architecture docs, API reference, roadmap, and blueprint. Files under docs/specs/done/ and docs/plans/done/ are terminal delivery evidence and may preserve superseded decisions.

Repository stage

The repository contains a verified P0 memory service with a shared TypeScript core, a Cloudflare Worker/D1 adapter, and a Bun/SQLite adapter. The dual-runtime contract suite passes on both runtimes. Automatic model-assisted derivation/reflection is implemented as an optional durable enrichment pipeline and remains disabled unless its complete extraction configuration is present. It is not production-activated until the locked evaluation and real runtime smokes are complete. The Astro dashboard uses the loopback same-origin adapter for live health, readiness, and authorized Memory Atlas data and has no synthetic fallback. Do not present opt-in enrichment or an undeployed dashboard as production activation evidence.

Required work lifecycle

Every change follows spec -> plan -> implement -> done. Read docs/engineering/requirements-workflow.md before substantial work.

  • Simple work may record its spec, plan, and evidence inline in the issue or pull request.
  • Complex work must create paired files under docs/specs/active/ and docs/plans/active/ before implementation.
  • Complex acceptance criteria must use identified EARS patterns and observable outcomes.
  • When scope changes, update the spec first and the plan second before continuing.
  • Completed, cancelled, or superseded work must move both artifacts to their matching done/ paths. Never report work as done while its spec or plan is still active or contains unchecked work.

Read the full file on GitHub · 106 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. 5d ago First seen · 106 lines · 968 tokens per session scan A c666c6227d23

Subscribe to this mod's changes

titen AGENTS.md is an instructions file published in the GitHub repository RamaAditya49/titen (12 stars, last pushed 5d ago), licensed Apache-2.0. It adds 968 tokens to every session, about $0.0048 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 2026-08-30.