walgit: Instructions file for Codex

AGENTS.md

walgit AGENTS.md is an instructions file for Codex, OpenCode from tobi/walgit. It costs 12,942 tokens per session, scanned A, original, MIT.

A set of instructions for people and AI agents contributing to the walgit repository, including its architecture, rules, and security requirements. Walgit is a Rust service that provides Git hosting over HTTP while storing durable data in an object-storage bucket.

In plain words
What is it for?
It helps agents and developers find the right design rules before changing code, configuration, routes, tests, or documentation.
Why use it?
It gives contributors one place to check how the repository works and which changes are allowed.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is tobi/walgit's own configuration. It tells Codex and OpenCode how to work on walgit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything walgit configures →

View source ↗ tobi/walgit
About the project

walgit is a single-binary Git server that stores repositories in an S3 or GCS object store instead of relying on a database or important local state. It serves Git fetches and pushes, Git LFS, repository browsing, an API, webhooks, and related repository features for deployments where machines act as disposable caches. The catalogue instruction helps coding agents work with this Git server.

tobi/walgit · 2,707 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to tobi/walgit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tobi/walgit/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/tobi/walgit

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for walgit AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tobi/walgit/agents-md/github.svg)](https://agentmods.dev/instructions/tobi/walgit/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tobi/walgit/agents-md"><img src="https://agentmods.dev/badge/instructions/tobi/walgit/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.

agentmods 80×15 button for walgit AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tobi/walgit/agents-md"><img src="https://agentmods.dev/badge/instructions/tobi/walgit/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12,942 This file is loaded in full into every session.
When invoked 12,942 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.12942 $0.12942
Opus 5.5 $0.05177 $0.05177
Sonnet 5.5 $0.02588 $0.02588
Haiku 4.5 $0.01294 $0.01294

Measured 1mo ago against content hash 983a89b91801, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

walgit AGENTS.md scanned grade A 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **The installer** (`crates/walgit-server/src/setup.rs`, POSIX sh, idempotent): git ≥ 2.46 + curl; pins a
AGENTS.md · 530 lines

How it starts

The opening of the file, as written. The whole thing — 530 lines — stays where its author put it; the contents beside it link to each section on GitHub.

walgit — architecture and operating manual for contributors (humans and agents)

Context: everyone, first. Read this before touching the repository: the constraints the design answers (§1), how the WAL works (§2), the principles a PR is judged against (§3), every design decision in force (§4), and the working rules (§5). Reading order starts at GOAL.md; §0 maps every other document.

No backwards compatibility (pre-1.0). We owe nothing to previous shapes of this system. Do not keep aliases, fallbacks, shims, deprecated routes, old config keys, old proto fields or migration code. When a decision changes the shape, delete the old shape in the same change: routes, clients, tests, docs, config keys. Data in the bucket is the one exception — WAL/manifest/log formats stay append-only and replayable, because the bucket is the repository; everything else is disposable. If you find yourself writing "still accepted for …" or "legacy", stop and remove the thing instead.

walgit serves git over smart HTTP (v0/v2), receive-pack, upload-pack, LFS and a browsing web UI, written in Rust, from disposable hosts whose only durable state is an object-store bucket. The reference workload it was built against is a 57 GiB / 73 M-object / 1.4 M-commit / 466 k-ref monorepo with LFS, served from machines whose "disk" is 20 GiB of tmpfs, next to a long tail of small repositories. The design follows Cursor's Git at any scale (Continuity); README.md tells the story, this file keeps the rules.

Doc Who / when to read it
GOAL.md Everyone, first. What walgit is for, the acceptance table, what we do not optimise for.
AGENTS.md (this) Everyone. Constraints §1, WAL §2, principles §3, decisions §4, working rules §5.
README.md The introduction: why (the Cursor lineage), what it does, how it works briefly, running it, invariants.
docs/PACKFILE_URI_DESIGN.md Anyone implementing pack groups, proofs, lifecycle, or negotiated delivery. Design target; later layers require separate implementation and evidence.
docs/PACKFILE_MIGRATION.md Bundle removal, saved settings, writer cutover, clients and rollout gates.
docs/spec/README.md Bounded models, contract identifiers, result semantics, code/test map and remaining verification gaps.
docs/ROUNDTRIPS.md Anyone touching a protocol that talks to the bucket (publish, sync, checkpoints, compaction/leases, remote reader, store backends). Round trips are the cost model; correct is not sufficient.
docs/POLICY.md Anyone touching receive-pack authorization or writing a repo policy. Normative rule language.
docs/LFS.md Anyone touching LFS (lfs.rs, lfs_upstream.rs) or importing a repository whose LFS history lives elsewhere.
docs/INTEGRITY.md Anyone touching import, the maintainer's fsck/repair units, or seeing connectivity: missing object on a push.
docs/EVENTS.md Anyone changing WAL-derived ref events, the webhook bridge, consumer semantics or event cursors.
docs/CONTRACT.md When you touch a crate boundary. The cross-crate contract; extend, don't rename; code wins where they differ.
docs/reference/cursor-git-at-any-scale.md The source design, verbatim. Read once before touching WAL/publish/sync/placement.
web/API.md UI/SDK authors and anyone changing web/*.rs. Wire contract, caching rules, SSE envelope, tasks, prefix-first lanes.
web/sdk/README.md Users of repos.js.
web/README.md Frontend engineers changing the React SPA, Vite build, SDK adapter, static assets, loading states.
walgit.example.toml Every config key with its default and a comment. Change it with the code.
walgit.standalone.toml The one-machine shape: walgit-server --config walgit.standalone.toml → https://walgit.localhost:8080/.
deploy/nginx.conf.example An optional nginx in front; documents the X-Accel-Redirect byte-offload contract.
Containerfile, flake.nix An OCI image; a Nix package, image and devshell.

Read the full file on GitHub · 530 lines

Changes

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.

  1. 1mo ago Changed · +83 lines · +1,223 tokens per session 983a89b91801
  2. 2mo ago First seen · 447 lines · 11,719 tokens per session scan A 4c0ff859f999

Subscribe to this mod's changes

walgit AGENTS.md is an instructions file published in the GitHub repository tobi/walgit (2,707 stars, last pushed 1mo ago), licensed MIT. It adds 12,942 tokens to every session, about $0.0518 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

walgit AGENTS.md compared with instructions from other repositories

walgit AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
walgit AGENTS.mdtobi/walgitInstructions file2.7k1mo agoMITA12,942Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode