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/dpanasenko-tech/claude-dev-pipeline/claude-mdgit clone --depth 1 https://github.com/dpanasenko-tech/claude-dev-pipelineWrote 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/dpanasenko-tech/claude-dev-pipeline/claude-md)<a href="https://agentmods.dev/instructions/dpanasenko-tech/claude-dev-pipeline/claude-md"><img src="https://agentmods.dev/badge/instructions/dpanasenko-tech/claude-dev-pipeline/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 5.1 | $0.06512 | $0.06512 |
| Opus 5 | $0.03256 | $0.03256 |
| Sonnet 5 | $0.01302 | $0.01302 |
| Haiku 4.5 | $0.00651 | $0.00651 |
Grade A, and why
claude-dev-pipeline CLAUDE.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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Operating Protocol
This file is the contract between you (Claude) and this project. It overrides any general defaults. Read it fully before any non-trivial action.
1. Project mission
Ship a production-grade B2B SaaS product incrementally without letting quality collapse. Every change must be safe to deploy, easy to review, and tied to a real user/business outcome.
2. Architecture guardrails
- Modular by default. Group code by feature (vertical slice), not by technical layer.
- No god-modules. A file > ~400 lines or a function > ~50 lines is a smell — split it.
- Boundaries are explicit. Cross-feature calls go through a stable public interface, not internals.
- Pure core, thin edges. Business logic is pure and testable; I/O sits at the edge.
- One source of truth per concept. No parallel implementations, no shadow models.
- Migrations are forward-only and reviewed. Never edit a shipped migration.
- External API clients implement a Protocol. Third-party API clients (
ExternalApiClient, etc.) must be injectable via constructor so tests pass a stub without network I/O.
3. Coding standards
- Names describe intent, not type.
userById, notgetUser. - Comments explain why, not what. Default to no comment.
- No dead code, no commented-out blocks, no
TODOwithout a ticket or owner. - Errors carry context; never swallow exceptions.
- Validate at the system boundary (HTTP, queue, CLI); trust internal types.
- No
any/Object/interface{}escape hatches without a written reason.
4. Task execution protocol
For any non-trivial change, the slice runs through six stages. Human approval gates are only at Stage 1 (brief) and Stage 2 (plan) — the product and architecture decisions. Once the plan (Stage 2) is approved and merged, the agent drives Stages 3–6A autonomously in a single consolidated PR (tests → code → adversarial review → release Phase A) without stopping for human review of intermediate stages. The next human checkpoint is release Phase A = GO on that PR: the human verifies GO and merges. Stage 6B (post-deploy: staging sync + Phase B + prod deploy) follows the merge. Any account can perform any stage.
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 · 306 lines · 6,512 tokens per session scan A 2ea17351e679
claude-dev-pipeline CLAUDE.md is an instructions file published in the GitHub repository dpanasenko-tech/claude-dev-pipeline (2 stars, last pushed 1mo ago), licensed MIT. It adds 6,512 tokens to every session, about $0.0326 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
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).
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.
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).