fullstack-director CLAUDE.md

fullstack-director CLAUDE.md is an instructions file for coding agents from IncommensurableHubris/fullstack-director. It costs 815 tokens per session, scanned A, original, MIT.

A set of operating instructions for Fullstack Director, a framework for guiding software projects through defined methods, rules, and checks.

In plain words
What is it for?
Running Fullstack Director in Claude Code and applying its project methodology, governance rules, verification states, and shared records.
Why use it?
It explains how the framework’s rules take precedence and how its Claude Code bridge should operate, reducing uncertainty about which instructions to follow.

Instructions file

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/incommensurablehubris/fullstack-director/claude-md
Clone the repo
git clone --depth 1 https://github.com/IncommensurableHubris/fullstack-director

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 fullstack-director CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/incommensurablehubris/fullstack-director/claude-md.svg)](https://agentmods.dev/instructions/incommensurablehubris/fullstack-director/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/incommensurablehubris/fullstack-director/claude-md"><img src="https://agentmods.dev/badge/instructions/incommensurablehubris/fullstack-director/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 815 This file is loaded in full into every session.
When invoked 815 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 $0.00815 $0.00815
Opus 5 $0.00407 $0.00407
Sonnet 5 $0.00163 $0.00163
Haiku 4.5 $0.00081 $0.00081

Measured 4d ago against content hash ce045b3a298f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fullstack-director 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 4d 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 · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@AGENTS.md

Fullstack Director — Claude Code bridge

AGENTS.md (imported above) is the portable entry point and applies on every harness. This file adds the methodology + governance layer and the Claude-specific operating notes. It is the index to the methodology, not a restatement of it.

Methodology

Fullstack Director is reuse-first and gate-driven: each skill keeps its proven machinery — assumption-mapping challenge, explicit gates, verification states, the DM-ID manifest — and changes only its reads/writes to the spine and its Reconcile wiring. The craft behind each phase lives in that skill's own references/; the why lives in the design-record commits (git history); the spine model and the amendment/subagent protocols live in shared/. The framework's own intent — mission + non-negotiables — lives in docs/charter.md (the Layer-A declaration layer): doctrine changes cite the charter item they serve, and a change contradicting one is user-gated, always.

Governance precedence

Two sources of truth, two derived views. When the framework runs on a project, authority resolves so:

  1. The project's spine Constitution (docs/spec/specification.md) — this project's intent. It wins on any product or scope question. It holds only that project's non-negotiables and must not restate framework principles (those are methodology — they live here, in shared/, and in the skills' references).
  2. Framework methodology (this file + shared/ + the skills' references) — how the work gets done. Subordinate to the project's intent on product/scope; authoritative on process.
  3. The project's AGENTS.md — a read-only emission of the Constitution, regenerated by 00-discovery on any Tier-2/3 amendment and by status. No independent authority: edit the Constitution and regenerate, never hand-edit the emission.
  4. Project CLAUDE.md — two framework-owned generated pieces: line 1 @AGENTS.md (the Claude Code bridge to the Constitution emission — created by 00-discovery only when the file is absent; an existing user file is advised, never edited) and § Current State (derived status only, written by status). Never a source of truth; the rest of the file is the user's. (GEMINI.md = the same bridge for Gemini CLI, one line @./AGENTS.md; Codex reads AGENTS.md natively.)

Read the full file on GitHub · 48 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. 4d ago First seen · 48 lines · 815 tokens per session scan A ce045b3a298f

Subscribe to this mod's changes

fullstack-director CLAUDE.md is an instructions file published in the GitHub repository IncommensurableHubris/fullstack-director (5 stars, last pushed 24d ago), licensed MIT. It adds 815 tokens to every session, about $0.0041 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.