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.
npx agentmods add instructions/ramaaditya49/titen/agents-mdgit clone --depth 1 https://github.com/RamaAditya49/titenWrote 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/ramaaditya49/titen/agents-md)<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>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 | $0.00968 | $0.00968 |
| Opus 5 | $0.00484 | $0.00484 |
| Sonnet 5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
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.
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:
docs/PRD.md— product contract;docs/architecture/overview.md— component boundaries;- relevant file under
docs/architecture/,docs/reference/, ordocs/deployment/; blueprint.mdonly 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/anddocs/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.
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.
- 5d ago First seen · 106 lines · 968 tokens per session scan A c666c6227d23
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.
Other instructions, from other repositories
agentic-context-engine AGENTS.md
Instructions for kayba-ai/agentic-context-engine, covering agents.md, repository guidelines, pipeline-first development (mandatory), core code protection and documentation maintenance.
activity-frames AGENTS.md
Instructions for nossa-y/activity-frames, covering can i install it without asking?, the mental model (10 seconds), fastest integration: mcp, from python and things you should not do.
agentic-context-engine CLAUDE.md
Instructions for kayba-ai/agentic-context-engine, covering claude.md, repository guidelines, pipeline-first development (mandatory), core code protection and documentation maintenance.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
honcho CLAUDE.md
Claude Code instructions for plastic-labs/honcho, covering claude.md, honcho overview, what is honcho?, core concepts and peer paradigm.
munkel CLAUDE.md
Claude Code instructions for limehq/munkel, covering claude.md, monorepo layout, commands, macos development specifics and deploy.