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/alirn76/panther/agents-mdgit clone --depth 1 https://github.com/AliRn76/pantherWrote 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/alirn76/panther/agents-md)<a href="https://agentmods.dev/instructions/alirn76/panther/agents-md"><img src="https://agentmods.dev/badge/instructions/alirn76/panther/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 5.1 | $0.01143 | $0.01143 |
| Opus 5 | $0.00571 | $0.00571 |
| Sonnet 5 | $0.00229 | $0.00229 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
panther 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 6d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
Panther is a Python 3.10+ async web framework focused on speed, simplicity, and practical API development. It is an ASGI framework with routing, request/response primitives, class-based and function-based APIs, OpenAPI support, WebSockets, middleware, authentication, permissions, throttling, caching, background tasks, templates, and database integrations.
When working in this repository, optimize for correctness first, then simplicity, then performance. Panther wants to stay small and fast, so prefer direct code paths and avoid adding abstraction unless it clearly reduces complexity.
Repository Map
panther/contains the framework source code.panther/main.pyis the ASGI application entrypoint and request dispatcher.panther/app.pycontainsAPIandGenericAPIendpoint handling.panther/routings.pycontains URL flattening, validation, and endpoint lookup.panther/request.pyandpanther/base_request.pydefine request parsing and request metadata.panther/response.pydefines response classes, serialization, streaming, templates, redirects, and files.panther/db/contains database connections, models, cursors, and query backends.panther/openapi/contains OpenAPI schema and documentation views.panther/panel/contains the built-in admin panel.panther/cli/contains command-line tooling.tests/contains the test suite.docs/docs/contains documentation pages.examples/contains example Panther applications.
Development Setup
Use Python 3.10 or newer.
python3.11 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
pip install -e .
Some tests need external services:
docker run --rm -p 27017:27017 -d --name mongo mongo
docker run --rm -p 6379:6379 -d --name redis redis
Test Commands
Prefer the project test runner because it runs test files individually for better isolation:
python tests
Useful variants:
python tests --not_mongodb
python tests --not_slow
python tests --not_mongodb --not_slow
python tests --mongodb
python tests --slow
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.
- 6d ago First seen · 156 lines · 1,143 tokens per session scan A 76e034f51baf
panther AGENTS.md is an instructions file published in the GitHub repository AliRn76/panther (355 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 1,143 tokens to every session, about $0.0057 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
laravel AGENTS.md
AGENTS.md instructions for laravel/laravel, covering laravel application, prerequisites and agent setup.
AgentEval copilot-instructions.md
Copilot instructions for AgentEvalHQ/AgentEval, covering agenteval - ai coding agent instructions, architecture overview, environment setup, optional: secondary models for comparison and build & test commands.
AgentEval tracing.instructions.md
Guidelines for implementing trace recording and replay.
zhin zhin-plugin.instructions.md
Instructions for zhinjs/zhin, covering zhin plugin runtime authoring, package contract, convention directories, imports and native typescript and command routes.
LarAgent AGENTS.md
Instructions for MaestroError/LarAgent, covering purpose, key principles, planning, executing plan and testing.
moosestack copilot-instructions.md
Instructions for 514-labs/moosestack, covering moose repository guide, code standards, required before each commit, development flow and repository structure.