Borrowing it
Nothing to install: this file belongs to SolNine-Git/agentless-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SolNine-Git/agentless-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/SolNine-Git/agentless-mcpWrote 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/solnine-git/agentless-mcp/agents-md)<a href="https://agentmods.dev/instructions/solnine-git/agentless-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/solnine-git/agentless-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/solnine-git/agentless-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/solnine-git/agentless-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00750 | $0.00750 |
| Opus 5.5 | $0.00300 | $0.00300 |
| Sonnet 5.5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
agentless-mcp 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 16d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for coding agents that work in this repository. The README describes the tools for their users; this file describes how to change them and how to prove a change did no harm.
Commands
uv sync --all-extras # the dev environment, mcp and tokens extras included
uv run pytest -q # unit and characterization suites
uv run pre-commit run --all-files # ruff, mypy, codespell, import-linter, deptry
Run both before you call a change done. Never silence a linter or the type checker; fix the code it points at.
Where things live
src/agentless_mcp/has four layers, enforced by the import-linter contracts inpyproject.toml:adapters -> application -> core -> prompts -> util. The CLI and MCP adapters are independent of each other. Change the design, not the contract, when an import does not fit.- Every caller-facing string (tool and parameter descriptions, refusals,
notes) lives in
src/agentless_mcp/prompts/*.json, with a typed field inprompts/__init__.py.tests/unit/test_prompts.pyformats each message with a sample of its placeholders, so a new message needs a sample there. tests/characterization/holds byte-exact goldens of the rendered output. Regenerate them deliberately, never reflexively: predict the diff, run the module'sregenerate(), and read the diff before you keep it.
Proving a change did no harm
Read docs/analysis/benchmark-methodology.md before you quote a benchmark figure or change anything that ranks, resolves or renders. Its section "The release regression gate" is the procedure a release follows:
- The suites and pre-commit, with every golden diff predicted.
- The Loc-Bench retrieval tier from a frozen copy of the build, with
ranked_filesbyte-diffed against the stored arm for the base commit. - The surface diff: both builds answer the same queries over the Loc-Bench checkouts, with tier transitions, a loss count, a prediction written down first, and a sample of changed lines read in the source.
- The exposure check before any paid agentic run.
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.
- 16d ago First seen · 65 lines · 750 tokens per session scan A d656c25447d3
agentless-mcp AGENTS.md is an instructions file published in the GitHub repository SolNine-Git/agentless-mcp (1 stars, last pushed today), licensed MIT. It adds 750 tokens to every session, about $0.0030 per session on Opus 5.5. 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 2026-10-10.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.