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/nymrel/nymrel-agent/agents-mdgit clone --depth 1 https://github.com/nymrel/nymrel-agentWrote 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/nymrel/nymrel-agent/agents-md)<a href="https://agentmods.dev/instructions/nymrel/nymrel-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/nymrel/nymrel-agent/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 | $0.00490 | $0.00490 |
| Opus 5 | $0.00245 | $0.00245 |
| Sonnet 5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
nymrel-agent 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nymrel Agent production operating boundary
This repository is the Nymrel-owned composition root for the Nymrel Agent product and implementation service. The public product is a stateless multi-model router; optional provider execution is customer-local and read-only in v0.1.
Allowed work
- Provider-neutral routing contracts, deterministic scoring, validation, receipts, tests, documentation, CLI, MCP, and the public routing Worker.
- Read-only local provider adapters that obtain credentials from environment-variable names in customer-owned configuration.
- Release packaging, public source publication, and deployment through the recorded production launch packet.
Five-minute release orientation
Before any release, deployment, or public-claim work, read docs/ONBOARDING.md and run its fail-before-work origin check. The only authoritative remote is https://github.com/Nymrel/nymrel-agent.git; legacy-jalenbuildshub is a retained historical reference and is never a release or deployment authority. Do not continue if the check fails.
Non-negotiable boundaries
- Never commit, print, transmit to the public router, or place in receipts any provider credential, prompt, task body, output body, customer data, or private studio artifact.
- The public API accepts routing metadata only and performs no model execution.
- Local execution remains read-only in v0.1. Do not add shell, filesystem-write, browser-mutation, outreach, purchase, deployment, or other side-effect tools without a separate isolation and authorization decision.
- Do not add hosted credential custody, accounts, billing, customer-data persistence, or model brokering without a separate protected-gate decision.
- Pi, OMP, and other runtimes may be optional subordinate adapters only; they do not replace the Nymrel-owned contract, router, policy, receipts, or release authority.
- Model scores and profile facts are caller-supplied evidence. Do not present them as Nymrel benchmarks or universal truth.
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 · 34 lines · 490 tokens per session scan A 2090d3cbeee6
nymrel-agent AGENTS.md is an instructions file published in the GitHub repository nymrel/nymrel-agent (0 stars, last pushed 5d ago), licensed MIT. It adds 490 tokens to every session, about $0.0024 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
openscreen AGENTS.md
AGENTS.md instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.
Claw3D AGENTS.md
Instructions for iamlukethedev/Claw3D, covering agent instructions, cursor cloud specific instructions, service overview, running the app and lint, typecheck, and tests.
commonly CLAUDE.md
Claude Code instructions for Team-Commonly/commonly, covering claude.md / agents.md, 🧠 product vision & architecture philosophy, what commonly is, the architecture model and key concepts.
claude-ads CLAUDE.md
Instructions for AgriciDaniel/claude-ads, covering claude ads repository instructions, architecture, development and verification.
openstatus AGENTS.md
AGENTS.md instructions for openstatusHQ/openstatus, covering agents.md, verify your change, toolchain, architecture and tests.
openstatus CLAUDE.md
Claude Code instructions for openstatusHQ/openstatus, covering claude.md and investigating production with polylane.