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/maxwellsantoro/dotrepo/agents-mdgit clone --depth 1 https://github.com/maxwellsantoro/dotrepoWrote 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/maxwellsantoro/dotrepo/agents-md)<a href="https://agentmods.dev/instructions/maxwellsantoro/dotrepo/agents-md"><img src="https://agentmods.dev/badge/instructions/maxwellsantoro/dotrepo/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 | $0.02834 | $0.02834 |
| Opus 5 | $0.01417 | $0.01417 |
| Sonnet 5 | $0.00567 | $0.00567 |
| Haiku 4.5 | $0.00283 | $0.00283 |
Grade A, and why
dotrepo 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 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.
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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents when working with code in this repository.
What This Is
dotrepo is an open metadata protocol for software repositories. It has three interlinked deliverables:
- A
.reposchema — versioned TOML manifests that encode provenance, trust, owners, docs, and build/test metadata - A reference toolchain — Rust CLI, stdio MCP server, and LSP for importing, validating, querying, syncing, and generating compatible surfaces
- A public index — a Git-backed collection of evidence-backed overlays and maintainer authority context at
index/repos/<host>/<owner>/<repo>/that makes public repos mechanically visible whether or not maintainers have adopted dotrepo natively
The public overlay index is generated and refreshed through an autonomous, evidence-constrained conveyor. Deterministic parsers run first; unresolved fields may escalate through progressively stronger model tiers; routine generated records do not wait for human review.
Documentation Authority
README.md— project overview and shipped capabilitiesROADMAP.md— strategy, active execution order, and milestone gatesCHANGELOG.md— release historydocs/README.md— documentation map- RFCs — design records and accepted contracts, not live task lists
When documentation conflicts, prefer current code and contracts, then
README.md for shipped behavior and ROADMAP.md for direction.
Commands
All Python tooling in this repository uses uv. Create the repository environment
with uv venv, then run Python commands, scripts, and tests with uv run. Never
invoke python, python3, pip, or pytest directly, and preserve this convention
in documentation, automation, subprocesses, and examples.
uv venv # Create the repository Python environment
uv sync --dev # Install locked Python development dependencies
cargo fmt --all -- --check # Format check (CI enforced)
cargo test --workspace # Run all tests
cargo build -p <crate-name> # Build specific crate
uv run python scripts/check_release_version.py # Release-version parity
# CLI
cargo run -p dotrepo-cli -- --root <path> validate
cargo run -p dotrepo-cli -- --root <path> query repo.name
cargo run -p dotrepo-cli -- --root <path> import --mode native
cargo run -p dotrepo-cli -- --root <path> generate --check
cargo run -p dotrepo-cli -- --root <path> trust
cargo run -p dotrepo-cli -- --root <path> doctor
cargo run -p dotrepo-cli -- validate-index
cargo run -p dotrepo-cli -- public export --index-root index --out-dir public --generated-at <time> --stale-after <time>
# MCP server (stdio JSON-RPC)
cargo run -p dotrepo-mcp
# LSP server (stdio JSON-RPC)
cargo run -p dotrepo-lsp
# Public export packaging
uv run python scripts/package_public_export.py --input public --output-dir dist
# Autonomous index batch (local, explicit opt-in)
uv run python scripts/run_autonomous_index_batch.py --skip-automation-enabled-check --output-dir /tmp/dotrepo-autonomous-batch
# Canonical public release gate
uv run python scripts/check_release_gate.py --output-root /tmp/dotrepo-release-gate --skip-vsix
# Python tests
uv run pytest
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 · 179 lines · 2,834 tokens per session scan A 768056384293
dotrepo AGENTS.md is an instructions file published in the GitHub repository maxwellsantoro/dotrepo (1 stars, last pushed 27d ago), licensed MIT. It adds 2,834 tokens to every session, about $0.0142 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
AgentNetworkProtocol AGENTS.md
AGENTS.md instructions for agent-network-protocol/AgentNetworkProtocol, covering repository guidelines, project structure & module organization, protocol ownership boundary, build, test, and development commands and coding style & naming conventions.
Cotal AGENTS.md
AGENTS.md instructions for Cotal-AI/Cotal, covering agents.md, what this is, read these first, commands and repository map.
nvim-mcp CLAUDE.md
Claude Code instructions for linw1995/nvim-mcp, covering claude.md, project overview, development commands, building and running and development build and run.
protocol-launcher AGENTS.md
AGENTS.md instructions for zhensherlock/protocol-launcher, covering agents.md - protocol launcher, repo shape, commands that matter, protocol library and docs.
protocol-launcher CLAUDE.md
Claude Code instructions for zhensherlock/protocol-launcher, covering claude.md - protocol launcher and claude-specific behavior.
GoSQLX CLAUDE.md
Instructions for ajitpratap0/GoSQLX, covering claude.md, project overview, architecture, core components and token processing pipeline.