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/johnfercher/maroto/agents-mdgit clone --depth 1 https://github.com/johnfercher/marotoWhat 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 | $0.00668 | $0.00668 |
| Opus 5 | $0.00334 | $0.00334 |
| Sonnet 5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
maroto 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This file guides any LLM, agent, or AI assistant (Claude, Copilot, Cursor, etc.) working on this repository. If you are such a tool, read this file first.
Skills
Standards and step-by-step conventions for common tasks live in
.github/skills. Before performing a task covered by one of
these skills, read the matching file and follow it exactly instead of
improvising:
| Skill | Use when |
|---|---|
| unit-tests.md | Writing or regenerating _test.go files |
| mocks.md | Generating mocks with mockery or writing mock expectations in a test |
| contribution.md | Preparing any change (branch, code, docs, PR) to meet the pull request checklist |
| code-quality.md | Writing or reviewing non-test Go code — what golangci-lint enforces and the SOLID patterns this codebase follows |
As new skill files are added to .github/skills, treat them as mandatory for
the task they cover.
Definition of Done
Before considering a change complete, follow contribution.md,
which walks through the full pull request checklist and ends with
running make dod (build + test + format + lint + codecov) with no golangci-lint issues.
codecov never fails the build, but its output (functions with 0% test coverage) is highly
recommended to address before opening the PR — see
contribution.md §8.
If make install-hooks has been run in this clone, make dod also runs automatically as a
pre-commit git hook (see .githooks/pre-commit) and blocks the commit
on failure — expect git commit itself to take as long as make dod does, and to fail the
commit if build/test/fmt/lint don't pass (codecov output won't block the commit, but don't
ignore it).
Contributing commands
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 · 50 lines · 668 tokens per session scan A 563224e01b1a
maroto AGENTS.md is an instructions file published in the GitHub repository johnfercher/maroto (2,750 stars, last pushed 14d ago), licensed MIT. It adds 668 tokens to every session, about $0.0033 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
gentelella copilot-instructions.md
Instructions for ColorlibHQ/gentelella, covering github copilot instructions — gentelella v4, hard rules, file layout, anti-patterns and commands.
table AGENTS.md
AGENTS.md instructions for TanStack/table, covering agent instructions and packages that cannot be upgraded yet.
mcp-read-website-fast CLAUDE.md
Instructions for just-every/mcp-read-website-fast, covering claude.md, project overview, core modules & files, commands and development.
base AGENTS.md
Instructions for basefoundry/base, covering ai agent guidance, working agreement, github workflow, repository release contract and validation.
base copilot-instructions.md
Instructions for basefoundry/base: Use AGENTS.md as the canonical workflow guidance for Base. These instructions exist to point Copilot at the same repository-owned rules used by other coding agents; they do not replace AGENTS.md, CONTRIBUTING.md, STANDARDS.md, or the .ai-context/ orientation files.
lazy-starter-kit CLAUDE.md
Instructions for Heoooooon/lazy-starter-kit: Follow the safety rules in AGENTS.md. In particular, never execute recursive rm directly; use lazy-safe-rm for a strict descendant of the current Git workspace.