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/hiepdnh/agentic-development-lifecycle/claude-mdgit clone --depth 1 https://github.com/hiepdnh/Agentic-Development-LifecycleWrote 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/hiepdnh/agentic-development-lifecycle/claude-md)<a href="https://agentmods.dev/instructions/hiepdnh/agentic-development-lifecycle/claude-md"><img src="https://agentmods.dev/badge/instructions/hiepdnh/agentic-development-lifecycle/claude-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 | $0.08038 | $0.08038 |
| Opus 5 | $0.04019 | $0.04019 |
| Sonnet 5 | $0.01608 | $0.01608 |
| Haiku 4.5 | $0.00804 | $0.00804 |
Grade C, and why
Agentic-Development-Lifecycle CLAUDE.md scanned grade C with 2 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Deny**: `git push`, `git reset --hard`, `rm -rf`, `curl`, `wget`, `nc` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Deny**: `git push`, `git reset --hard`, `rm -rf`, `curl`, `wget`, `nc` How it starts
The opening of the file, as written. The whole thing — 543 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Agentic Development Lifecycle
Framework hỗ trợ toàn bộ SDLC cho mọi role. Dùng được cho bất kỳ team nào muốn AI assistance có cấu trúc.
Developing This Framework
This repo IS the framework source. Two hand-maintained skill trees serve as canonical sources:
.claude/skills/— Claude Code Agent Skills (35 skills × 3 langs = 105SKILL*.mdfiles). Each skill is a flat folder.claude/skills/<role-command>/holdingSKILL.md(VN) +SKILL.en.md+SKILL.ja.md. Skills auto-trigger from theirdescriptionfrontmatter and can also be invoked explicitly as/role-command(e.g./ba-spec)..opencode/skills/— OpenCode hand port (102 files) withtask()/question()syntax, nested<role>/<name>.md, invoked asrole:command.
Cursor, Antigravity, Codex CLI, and Copilot CLI targets are generated at install time from these sources — no separate hand-maintained tree:
- Cursor →
bin/transformers/cursor.jstransforms.claude/skills/*/SKILL.md→.cursor/rules/*.mdc(one flat.mdcper skill; rewrites frontmatter todescription+globs: []+alwaysApply: false; strips the# Skill:prefix; relabelsAgent(...)blocks asSub-task Agent(...)). Cursor Agent is single-agent, so multi-agent skills execute inline. - Antigravity →
bin/transformers/antigravity.jscopies.opencode/skills/*→.antigravity/skills/*(alias — OpenCodetask()/question()syntax is reused since Antigravity's skill convention is not yet stable). - Codex CLI →
bin/transformers/codex.jstransforms.claude/skills/*/SKILL.md→.agents/skills/*/SKILL.md(rewritesAskUserQuestion/Agent(...)/model hints into host-neutral prose; copies referencedagents/*.mdcontracts into areferences/subfolder). - Copilot CLI →
bin/transformers/copilot.jstargets.github/skills/*/SKILL.md(Copilot CLI reads the same SKILL.md standard as Codex) by delegating tocodexTransformer.copyAndTransformwithcontractLabel: 'Copilot CLI'— no separate transform logic, since the host-neutral rewrite is identical. New; not yet smoke-tested against a live Copilot CLI session.
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 · 543 lines · 8,038 tokens per session scan C 60193ab7641a
Agentic-Development-Lifecycle CLAUDE.md is an instructions file published in the GitHub repository hiepdnh/Agentic-Development-Lifecycle (6 stars, last pushed 8d ago), licensed MIT. It adds 8,038 tokens to every session, about $0.0402 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
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.
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 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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.