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/shenjianan97/persistent-agent-runtime/agents-mdgit clone --depth 1 https://github.com/shenjianan97/persistent-agent-runtimeWrote 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/shenjianan97/persistent-agent-runtime/agents-md)<a href="https://agentmods.dev/instructions/shenjianan97/persistent-agent-runtime/agents-md"><img src="https://agentmods.dev/badge/instructions/shenjianan97/persistent-agent-runtime/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 | $0.05024 | $0.05024 |
| Opus 5 | $0.02512 | $0.02512 |
| Sonnet 5 | $0.01005 | $0.01005 |
| Haiku 4.5 | $0.00502 | $0.00502 |
Grade A, and why
persistent-agent-runtime 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 4d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Project Navigation
Project
Cloud-Native Persistent Agent Runtime — durable execution for AI agents.
Stack: Java + Spring Boot (API) · Python (worker) · TypeScript + React 19 + Vite (Console) · PostgreSQL · LangGraph. See ARCHITECTURE.md for full stack and rationale.
Documentation Map
docs/product-specs/— What the system should do (vision, user stories, core concepts)docs/design-docs/— How to build itcore-beliefs.md— Architectural invariantsphase-N/design.md— Primary design doc per phaselangfuse/,agent-capabilities/,phase-3-plus/— Cross-cutting and forward-looking
docs/exec-plans/active/anddocs/exec-plans/completed/— Implementation plansdocs/LOCAL_DEVELOPMENT.md— Local setup and environment
Services
services/api-service/— Spring Boot REST API (README)services/console/— React SPA (README)services/worker-service/— Python worker (README)services/model-discovery/— Model discovery service
Common Commands
make help # list all targets with descriptions
make init # first-time setup
make install # install deps across services
make test # unit tests (fast, no infra)
make e2e-test # E2E on per-worktree isolated infra (DB 55433 on primary checkout; dynamic in worktrees)
make test-all # unit + E2E
make start # live stack: Console :5173, API :8080
make stop # stop live stack
make status # background-target status
# Python (worker) — always use the pinned venv:
services/worker-service/.venv/bin/python ...
New Phase Workflow
- Spec → Add phase sections to
docs/product-specs/(vision.md, user-stories.md, core-concepts.md) - Design → Create
docs/design-docs/phase-N/design.md - Plan → Create
docs/exec-plans/active/phase-N/with plan.md, progress.md, agent_tasks/ - Execute → Implement per the task specs
- Archive → Move
active/phase-N/→completed/phase-N/ - Update status → Update STATUS.md
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.
- 4d ago First seen · 186 lines · 5,024 tokens per session scan A 7832038a634a
persistent-agent-runtime AGENTS.md is an instructions file published in the GitHub repository shenjianan97/persistent-agent-runtime (154 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 5,024 tokens to every session, about $0.0251 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.