Borrowing it
Nothing to install: this file belongs to KashZod/devloop. 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/KashZod/devloop/main/AGENTS.mdgit clone --depth 1 https://github.com/KashZod/devloopWrote 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/kashzod/devloop/agents-md)<a href="https://agentmods.dev/instructions/kashzod/devloop/agents-md"><img src="https://agentmods.dev/badge/instructions/kashzod/devloop/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/kashzod/devloop/agents-md"><img src="https://agentmods.dev/badge/instructions/kashzod/devloop/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 | $0.00452 | $0.00452 |
| Opus 5 | $0.00226 | $0.00226 |
| Sonnet 5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
devloop 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 today.
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.
What it actually says
AGENTS.md
Project rules for any agent working in this repository. devloop is a
test-driven development loop for AI coding agents, shipped as a plugin for
Claude Code and Codex. The product is prompt text: three skills under
skills/, three review agents under agents/.
The full engineering config lives in
.devloop/config.md (build and test commands,
architecture patterns, standards to verify, blindspots, commit conventions)
and the domain context in .devloop/domain.md. Read
config.md before reviewing or changing anything under skills/ or
agents/. Those files are the canonical home for the rules; this file exists
because it is the harness-native one, and it stays short on purpose.
Before you commit
- Run
./validate.sh. It must report 0 failed. It is the only automated test in this repo. - Use standard punctuation. No em dashes and no en dashes in any published file. The suite enforces this; writing them anyway just costs a cycle.
- Commit mechanics (staging discipline, bumping both plugin manifests
together) live in
.devloop/config.mdunder Commit Conventions. That is their canonical home; they are not restated here, so the two files cannot drift.
While you work
- Keep skill and agent prose harness-agnostic. State the intent and let the harness supply the mechanism. Naming a Claude Code keystroke or a Codex command breaks the other harness and fails the suite.
- Working notes go in
.local-docs/(gitignored).docs/is the published GitHub Pages site, not a scratch directory. - A prompt change is a behavior change. Reading the diff does not tell
you whether a review agent's recall moved. Do not claim a review-agent
improvement that only inspection supports; see the last standard in
.devloop/config.md.
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.
- today First seen · 39 lines · 452 tokens per session scan A a283ff82c561
devloop AGENTS.md is an instructions file published in the GitHub repository KashZod/devloop (2 stars, last pushed today), licensed Apache-2.0. It adds 452 tokens to every session, about $0.0023 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 2026-09-12.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).