pdlc-autopilot: Instructions file for Claude Code

CLAUDE.md

pdlc-autopilot CLAUDE.md is an instructions file for Claude Code from vishnujayvel/pdlc-autopilot. It costs 1,531 tokens per session, scanned A, original, MIT.

A project-specific instruction file describing conventions and safeguards for the PDLC Autopilot codebase, including shell scripts, state files, and handoff records.

In plain words
What is it for?
Use it when working on PDLC Autopilot's hooks, shell scripts, state handling, or handoff documents.
Why use it?
It gives a coding agent rules for changing this project without breaking its file formats, error handling, or platform compatibility.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; positional $N argument.

This is vishnujayvel/pdlc-autopilot's own configuration. It tells Claude Code how to work on pdlc-autopilot 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 pdlc-autopilot configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vishnujayvel/pdlc-autopilot. 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/vishnujayvel/pdlc-autopilot/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/vishnujayvel/pdlc-autopilot

Made for: Claude Code.

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 pdlc-autopilot CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vishnujayvel/pdlc-autopilot/claude-md/github.svg)](https://agentmods.dev/instructions/vishnujayvel/pdlc-autopilot/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vishnujayvel/pdlc-autopilot/claude-md"><img src="https://agentmods.dev/badge/instructions/vishnujayvel/pdlc-autopilot/claude-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 pdlc-autopilot CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/vishnujayvel/pdlc-autopilot/claude-md"><img src="https://agentmods.dev/badge/instructions/vishnujayvel/pdlc-autopilot/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,531 This file is loaded in full into every session.
When invoked 1,531 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.01531 $0.01531
Opus 5 $0.00766 $0.00766
Sonnet 5 $0.00306 $0.00306
Haiku 4.5 $0.00153 $0.00153

Measured 8d ago against content hash 7e9fdbf9b7ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pdlc-autopilot 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 8d 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.

CLAUDE.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — PDLC Autopilot

Project Overview

PDLC Autopilot is a CLI skill for Claude Code that orchestrates autonomous product development lifecycles using a Director/Actor/Critic pattern.

Code Conventions

Shell Scripts (hooks/)

  • All hook scripts MUST exit 0, even on error. Use trap 'exit 0' ERR (or trap '...; exit 0' ERR if output is needed).
  • Use set -eo pipefail at the top of hook scripts that have ERR traps (-u / nounset bypasses the ERR trap and breaks fail-open). Use set -euo pipefail in library scripts without ERR traps.
  • Use local only inside function bodies. Never use local in the main script body or inside loops/conditionals outside functions (macOS bash 3.2 fatal error).
  • Atomic writes: write to .tmp then mv to final path. Never write directly to state files.
  • HANDOFF.md uses flat YAML frontmatter (no nested objects). Parse with awk, not yq.
  • pdlc_get_field / pdlc_set_field in hooks/lib/pdlc-state.sh are the canonical state accessors. Do not reimplement frontmatter parsing inline.
  • Use substr($0, length(key)+3) in awk to preserve values containing : . Never use just $2 with -F': ' for value extraction.
  • Prefer single-word values in HANDOFF.md fields (e.g., PASS_WARN not PASS WITH WARNINGS) to avoid word-splitting issues.
  • Environment variable names: PDLC_ prefix for all configurable vars.

Process Enforcement

  • SpecGate (hooks/spec-gate.sh): Blocks spec generation via Task tool. Specs must use Kiro skills.
  • CriticGate (hooks/critic-gate.sh): Blocks Actor dispatch without prior critic review.
  • Stop Guard (hooks/pdlc-stop-check.sh): Blocks exit when PDLC tasks are incomplete.
  • Deny messages use <error-recovery> XML framing for LLM self-correction.
  • The "matcher": "Task" in settings.json ensures gate hooks only fire for Task tool calls.
  • PDLC_DISABLED=1 bypasses all blocking hooks (SpecGate, CriticGate, Stop Guard, Outer Loop). Used during self-development to avoid bootstrapping circularity. External governance provided by GitHub Spec Kit (.specify/).

Read the full file on GitHub · 76 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. 8d ago First seen · 76 lines · 1,531 tokens per session scan A 7e9fdbf9b7ff

Subscribe to this mod's changes

pdlc-autopilot CLAUDE.md is an instructions file published in the GitHub repository vishnujayvel/pdlc-autopilot (6 stars, last pushed 2mo ago), licensed MIT. It adds 1,531 tokens to every session, about $0.0077 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 2026-09-04.

Related

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.

github/spec-kit · 7,126 tokens

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens