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/elastic/jingra/agents-mdgit clone --depth 1 https://github.com/elastic/jingraWhat 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 | $0.00387 | $0.00387 |
| Opus 5 | $0.00193 | $0.00193 |
| Sonnet 5 | $0.00077 | $0.00077 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
jingra 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.
What it actually says
AGENTS
- Source of truth: Only this file defines the project instructions.
CLAUDE.mdand.cursor/rules/jingra-project.mdcmust symlink to it. After cloning, run./ensure-agent-links.shonce. - Environment: Use Java 21 from
.envrc. Run commands withsource .envrc && <command>, for examplesource .envrc && make test. - TDD first: For every new behavior or bug fix, write or update the test first.
- Show the test first: Show the new or changed test, or the diff, before changing implementation code.
- Then implement: Change the code only until the tests pass.
- Do not fake passing tests: Do not weaken assertions, remove valid test cases, or loosen mocks to hide bugs.
- Do not skip flaky tests: Do not claim a flaky test can simply be skipped.
- If a test is wrong: Say so clearly. Fix the test in a separate step and explain why.
- Green build means correct behavior: A green build only counts if the behavior is actually correct, not if the test suite was gamed.
- No fixed sleeps: Do not use
Thread.sleepor fixed delays for coordination, retries, backpressure, or waiting for readiness. - Use proper concurrency tools instead: Prefer
ExecutorService,CompletableFuture,awaitTermination,CountDownLatch,Phaser, bounded blocking queues, or polling with a timeout. - For async or eventual tests: Use Awaitility or a similar tool. Do not use sleeps.
TOOLING
This project is developed using Cursor and Claude Code as AI-assisted development tools.
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.
- 2d ago First seen · 24 lines · 387 tokens per session scan A f08ab53fc305
jingra AGENTS.md is an instructions file published in the GitHub repository elastic/jingra (6 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 387 tokens to every session, about $0.0019 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.
Other instructions, from other repositories
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.
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).
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.