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 skills add Khar-AG/t-800-agent --skill t-800-factory-scaffoldgit clone --depth 1 https://github.com/Khar-AG/t-800-agentWrote 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/skills/khar-ag/t-800-agent/t-800-factory-scaffold)<a href="https://agentmods.dev/skills/khar-ag/t-800-agent/t-800-factory-scaffold"><img src="https://agentmods.dev/badge/skills/khar-ag/t-800-agent/t-800-factory-scaffold/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.
<a href="https://agentmods.dev/skills/khar-ag/t-800-agent/t-800-factory-scaffold"><img src="https://agentmods.dev/badge/skills/khar-ag/t-800-agent/t-800-factory-scaffold.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00100 | $0.00527 |
| Opus 5 | $0.00050 | $0.00264 |
| Sonnet 5 | $0.00020 | $0.00105 |
| Haiku 4.5 | $0.00010 | $0.00053 |
Grade A, and why
t-800-factory-scaffold 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 9d 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
T-800 — CREATE scaffold (procedural)
Это не субагент. CREATE-артефакты пишет только Task(t-800-factory) (внутри: architect→…→auditor).
Что читать
shared/department-orchestration-contract.mdshared/plan-to-factory-handoff-contract.mdshared/project-memory-contract.md{memory_path}/factory-briefs/<slug>.yaml
Детали: create-checklist.md, department-order.md.
Алгоритм
- Discovery:
bash scripts/discover-target-project.sh --workspace "<ROOT>"→ запомниmemory_path. - Confirm brief +
STATE.md(init/touch через loop scripts). - Порядок отделов: intake? → scout → research-lead → prompt-craft? → brain-lead → factory.
- Factory АВТО: architect → builder → … → auditor (листов не звать вручную).
- Перед «готово» — skill
t-800-run-gates/t800_run_gate.py. - После каждого отдела — одна строка progress пользователю.
Выход
phase: scout|research|craft|brain|factory|gates
next_task: "Task(t-800-…)" | null
blockers: []
Без production Write вне factory.
Связи
- Invoked by: director / factory CREATE
- Companions:
t-800-run-gatesпосле auditor
Запреты
- Write/StrReplace в
agents/,skills/,commands/,rules/,hooksиз skill - Skip factory / invent new research|brain agents
- MIR вне
~/.cursor/plugins/local/
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 56 lines · 100 tokens per session scan A 2d34f290c40f
t-800-factory-scaffold is a skill published in the GitHub repository Khar-AG/t-800-agent (8 stars, last pushed 16d ago), licensed MIT. It adds 100 tokens to every session and 527 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
pn-godot-dev
Guides Godot Engine 4.x development: GDScript, GDExtension (C++), multiplayer, VisualShader/shader code, export/platform config, autoloads, Resource serialization, InputMap, headless CI, AnimationPlayer/Tree, 2D/3D workflows, physics, PCG, and Blender pipeline. Use when developing Godot 4.x projects.
pn-session-retro
Run a blameless retrospective on an agent transcript. Classify mistakes under a 5-code taxonomy, emit a structured report at docs/refs/retros/, and recommend concrete hardening. Use after a session that felt off, before a quarterly audit, or via the /pn-retro command. v1 is manual-only; cross-session pattern counters…
pn-gsap
Deep GSAP API reference — timelines, easing, ScrollTrigger, plugins (SplitText, Flip, DrawSVG, MorphSVG, MotionPath), framework integrations (React useGSAP, Vue, Svelte), and performance patterns. Use when implementing GSAP-powered animations; load alongside pn-animation for motion role taxonomy and budgets.
pn-business-strategy-orchestration
Conductor for the businessstrategy workflow. Defines workflow state shape, companion-MCP detection, evidence-log protocol, HITL gate scripts, discussion-loop semantics, and explicit references to all sub-skills. Load at step 0 and keep loaded throughout the run.
pn-a2a-interop
Design and implement Agent2Agent (A2A) Protocol integrations — connecting pnCore-orchestrated agents with external agents built on other frameworks (LangGraph, ADK, CrewAI, AutoGen) or owned by other organizations. Covers A2A service cards, task routing, trust/auth, capability negotiation, and audit trail. Use when a…
pn-cx-agent-patterns
Design and build customer-facing AI agents — concierge-style service agents, agentic commerce flows (session memory, preference recall, multi-turn negotiation, delegated transaction execution), and hyper-personalized CX pipelines. Use when building customer support agents, shopping assistants, booking agents, or any…