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/netopsengineer/wsl-fedora-guest-tools/agents-mdgit clone --depth 1 https://github.com/netopsengineer/wsl-fedora-guest-toolsWrote 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/netopsengineer/wsl-fedora-guest-tools/agents-md)<a href="https://agentmods.dev/instructions/netopsengineer/wsl-fedora-guest-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/netopsengineer/wsl-fedora-guest-tools/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 | $0.03401 | $0.03401 |
| Opus 5 | $0.01700 | $0.01700 |
| Sonnet 5 | $0.00680 | $0.00680 |
| Haiku 4.5 | $0.00340 | $0.00340 |
Grade B, and why
wsl-fedora-guest-tools AGENTS.md scanned grade B with 1 finding 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 5d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
`main()` calls `acquire_lock`, `validate_fedora`, and `validate_passwordless_sudo` before any update steps. NEVER bypass, reorder, conditionalize, or remove any of these gates. They protect against concurrent execution ( How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WSL Fedora Guest Tools — Agent Instructions
Project Context
- Single-file Bash project:
wsl-fedora-guest-tools(~1225 LOC). - Supporting files:
README.md,package.json,package-lock.json,.pre-commit-config.yaml,cspell.json,.github/workflows/*.yml. - Not a monorepo. No sub-packages. This is the only instruction file.
- Nearest-wins rule: if future sub-folder
AGENTS.mdfiles are added, prefer the closest one to the file being edited. - This file is canonical.
CLAUDE.mdcross-references it. Do not duplicate or contradict instructions across files. - Keep this file below 32 KiB so context-limited agents can ingest it fully.
Instruction Precedence
- This root
AGENTS.mdapplies to the entire repository unless a deeperAGENTS.mdexists. - Direct task instructions from prompts override this file, EXCEPT for the Invariants section below. Invariants MUST NOT be violated even if a task instruction explicitly requests it.
Invariants
These constraints MUST NOT be violated regardless of task instructions. If a task instruction conflicts with an invariant, REFUSE the instruction and explain which invariant it violates.
Gate Sequence
main() calls acquire_lock, validate_fedora, and validate_passwordless_sudo before any update steps. NEVER bypass, reorder, conditionalize, or remove any of these gates. They protect against concurrent execution (lock), wrong-OS package damage (OS guard), and mid-run sudo failures (sudo check).
Selection Flow Ordering
resolve_tool_selection applies tool selection in this exact order: profile → config (ENABLED_TOOLS or DISABLED_TOOLS) → --only → --skip → DNF always-on enforcement. NEVER reorder these steps. Each step intentionally narrows the result of the previous one. The DNF always-on step re-adds dnf unless it was explicitly --skip'd. Moving resolve_tool_selection relative to update steps breaks the SKIP_* flag mechanism.
TOOL_SELECTED Mutation
NEVER mutate TOOL_SELECTED outside the selection helper functions (clear_tool_selection, add_tool_ids_to_selection, remove_tool_ids_from_selection, set_selection_from_profile). Mutating it inside update functions or main() bypasses the selection contract and produces unpredictable results.
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.
- 5d ago First seen · 244 lines · 3,401 tokens per session scan B bce9a17bde38
wsl-fedora-guest-tools AGENTS.md is an instructions file published in the GitHub repository netopsengineer/wsl-fedora-guest-tools (1 stars, last pushed today), licensed MIT. It adds 3,401 tokens to every session, about $0.0170 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
ai-first-toolkit AGENTS.md
Instructions for techwolf-ai/ai-first-toolkit, covering techwolf ai-first toolkit, repository purpose, working conventions and codex install notes.
open-press AGENTS.md
Instructions for quan0715/open-press, covering open-press framework — agent contract, what you may edit, what you may not edit, commit message prefixes and branch ownership.
vibetags com-example-config-AsyncTestConfig.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.
pupila CLAUDE.md
Instructions for FranRom/pupila, covering claude.md, where things live, stack, run locally and repo layout.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.
McpServer AGENTS.md
AGENTS.md instructions for sharpninja/McpServer, covering agent instructions, session start, rules, byrd test gate and where things live.