agentmods.dev

cli AGENTS.md

Coding instructions for a TypeScript command-line application that manages DevCycle feature flags, which control how software features are enabled. The project also includes an API client, authentication and a Model Context Protocol server.

In plain words
What is it for?
It helps develop CLI commands, API and authentication code, interactive output, utilities and the MCP server.
Why use it?
It keeps changes consistent with the project's directory structure, Yarn tooling, formatting and commit conventions.

Instructions file for CodexOpenCode

20 15d ago A scan 1,305 tokens original MIT
View the source file DevCycleHQ/cli
Install

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.

agentmods
npx agentmods add instructions/devcyclehq/cli/agents-md
Clone the repo
git clone --depth 1 https://github.com/DevCycleHQ/cli

Made for: Codex, OpenCode.

Per session 1,305 This file is loaded in full into every session.
When invoked 1,305 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01305 $0.01305
Opus 5 $0.00652 $0.00652
Sonnet 5 $0.00261 $0.00261
Haiku 4.5 $0.00130 $0.00130

Measured 2d ago against content hash 7b81fcc3b6d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cli 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.

AGENTS.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DevCycle CLI Coding Standards and Conventions

Project Structure

TypeScript CLI application built with oclif framework for DevCycle feature flag management.

Main Entry Points

  • CLI Binary: bin/run - Main CLI entry point
  • MCP Server: dist/mcp/index.js - Model Context Protocol server
  • Source Root: src/index.ts - TypeScript entry point

Core Directories

  • src/commands/ - All CLI commands organized by feature
  • src/api/ - API client code and schemas
  • src/auth/ - Auth handling (API keys, SSO, tokens)
  • src/ui/ - Interactive prompts and output formatting
  • src/utils/ - Shared utilities and helpers
  • src/mcp/ - Model Context Protocol implementation

Configuration and Tooling

  • Uses Yarn with workspaces
  • Always use yarn not npm

Formatting

  • Defer all formatting to Prettier for supported file types (JavaScript, TypeScript, JSON, Markdown, etc.)

Git Commit Message Conventions

  • Follow Conventional Commits specification: <type>: <description> (scopes rarely used)
  • Valid types: feat, fix, docs, style, refactor, perf, test, build, ci, chore, revert
  • Description should be imperative mood, lowercase, single sentence
  • Examples: feat: add support for multi-threaded tests, fix: correct response for invalid input

Aviator CLI Workflow (optional)

  • Use Aviator CLI (av) for managing stacked branches: av branch chore-fix-invalid-input
  • Sync and push changes: av sync --push=yes
  • Create PR: av pr --title "<title>" --body "<body>"
    • Title follows Conventional Commits, body uses markdown/bullets
    • av pr will push the branch
  • GitHub PR descriptions should be short and focus on why changes were made, not what changed, limit describing files and tests changed.

Naming Conventions

  • Use camelCase for files, folders, and variables (starting with lowercase)
  • PascalCase for classes and interfaces
  • SCREAMING_SNAKE_CASE for constants
  • kebab-case for CLI flags and file names

Read the full file on GitHub · 168 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. 2d ago First seen · 168 lines · 1,305 tokens per session scan A 7b81fcc3b6d6

Subscribe to this mod's changes

cli AGENTS.md is an instructions file published in the GitHub repository DevCycleHQ/cli (20 stars, last pushed 15d ago), licensed MIT. It adds 1,305 tokens to every session, about $0.0065 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.

Backend and APIsData and AIDevOps and cloudcontinuous-deliverycontinuous-deploymentdevcyclefeature-flagsfeature-togglesopenfeature
Related

Other instructions, from other repositories

flux-operator AGENTS.md

AGENTS.md instructions for controlplaneio-fluxcd/flux-operator, covering agents instructions, project overview, repository structure, rules of engagement for ai agents and development commands for ai agents.

controlplaneio-fluxcd/flux-operator · 770 tokens

ninthwave CLAUDE.md

Instructions for ninthwave-io/ninthwave, covering ninthwave, development, architecture, conventions and test safety.

ninthwave-io/ninthwave · 1,812 tokens

bq-analytics CLAUDE.md

Instructions for johnkueh/bq-analytics, covering bq-analytics — claude notes and releases publish on tag push, not on branch push.

johnkueh/bq-analytics · 287 tokens

eac CLAUDE.md

Claude Code instructions for ready-to-release/eac, covering eac monorepo, key modules, critical isolation constraint, mcp servers and git policy.

ready-to-release/eac · 523 tokens

spinnaker-mcp CLAUDE.md

Claude Code instructions for GeiserX/spinnaker-mcp, covering claude.md — spinnaker-mcp, tech stack, development, run locally and architecture.

GeiserX/spinnaker-mcp · 432 tokens

flagskit AGENTS.md

Instructions for flagskit/flagskit, covering flagskit — feature flags, setup, provider, useflag and useflags.

flagskit/flagskit · 1,102 tokens