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/koldovsky/project-factory/agents-mdgit clone --depth 1 https://github.com/koldovsky/project-factoryWhat 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 | $0.00508 | $0.00508 |
| Opus 5 | $0.00254 | $0.00254 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
project-factory 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 3d 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.
What it actually says
This is NOT the Next.js you know
This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in node_modules/next/dist/docs/ before writing any code. Heed deprecation notices.
This repo is a multi-tool plugin (Claude Code · Cursor · Codex · Copilot), with
AGENTS.md+ theproject-factoryskill as the portable core. Seedocs/portability.mdand the README for install per tool.
Maintaining the skill: skills/project-factory/ is self-contained — its
references/ holds generated mirrors of the canonical orchestration docs
(MASTER-PROMPT.md, LOOP.md, checklists/quality-gates.md,
commands/{init,onboard}.md). After editing any of those, run
node scripts/sync-skill-refs.mjs to refresh the mirrors. --check fails if
they are stale (wire it into CI if you add one).
Use docs/requirements.md to understand the requirements for the project.
Project Handoff Protocol
Before planning or implementing any substantive change, read:
docs/current-state.mdfor the latest persistent handoff and next-step guidance.docs/mvp-capability-plan.mdfor the MVP change sequence and capability scope.openspec/project.mdand the relevant files underopenspec/specs/for current accepted behavior.docs/adr/for accepted architecture decisions.
Keep docs/current-state.md current when a meaningful milestone happens, especially when:
- an OpenSpec change is created, implemented, validated, or archived;
- a capability moves from planned to implemented;
- setup instructions, validation expectations, or known blockers change;
- architectural decisions are accepted or replaced.
docs/current-state.md is a handoff aid, not the source of truth. If it conflicts with code, OpenSpec specs, ADRs, or tests, verify the repo state and update the handoff file.
Write last update date/time and the current phase of the project in the file (use Kyiv time zone). Example:
- **Date and time:** 2026-04-29 16:40:00
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.
- 3d ago First seen · 44 lines · 508 tokens per session scan A 5dccd27d8cd8
project-factory AGENTS.md is an instructions file published in the GitHub repository koldovsky/project-factory (4 stars, last pushed 1mo ago), licensed MIT. It adds 508 tokens to every session, about $0.0025 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
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.