Standard Template Construct

One source of truth for
AI agent infrastructure.

Your coding agent's rules, memory, skills, hooks, and tools — authored once in a harness-neutral form, then deployed into any concrete harness. Edit in one place; drift becomes impossible by construction.

In Warhammer 40k lore, an STC is a relic that emits complete, reproducible blueprints adapted to the materials at hand. This project borrows the idea for your agent's configuration.

Why

One system, not three features

STC rests on three pillars. Two are engines — a single source of knowledge and an encoded software lifecycle; both cut what the agent has to spend. The third, a lean token economy, is the result they add up to — reinforced by a few dedicated savings of its own.

results in + direct mechanics · output→file · offload · cheapest model Single source of knowledge memory · wiki-links · ADRs Encoded SDLC spec · test · review · docs Lean token economy the result of both

Knowledge lets the agent look a fact up instead of re-deriving it — fewer tokens spent searching. The SDLC keeps every change specced, tested and reviewed on the way in, docs in one place — so maintenance and edits never spiral. The token economy is what both add up to — plus a few dedicated mechanics of its own; and as a bonus, the work itself comes out faster and more coherent.

01 Single source of knowledge

Local-first markdown memory with [[wiki-links]] and link-integrity checking. The agent stops re-deriving hard-won project knowledge every session — and the same knowledge travels across model providers unchanged.

→ fewer search & derivation tokens

02 Encoded SDLC · SDD → TDD

A Plan → Do → Verify loop, spec & task generators, a TDD skill, and a fresh-context three-agent review (correctness + security + QA) feeding a self-improving defect ledger. Changes ship small, tested and documented.

→ less rework, cheaper maintenance

03 Lean token economy

The result of the first two — plus hygiene mechanics: raw output routed to files, expensive jobs offloaded to sub-agents, web search isolated in one research agent, each task on the cheapest capable model.

→ less waste, faster sessions

How it works

Author once. Deploy to any harness.

You write capabilities once, in a harness-neutral form, in core/. Adapters declare how each harness realises them. A Python deploy pipeline renders the result into the concrete harness directory — adapted to its format.

# write once, in harness-neutral form
STC/
├── core/        # universal blueprints — rules, memory, skills, hooks, commands
├── user/        # your private config — profile, project notes, secrets
├── adapters/    # per-harness descriptors — how core/ maps onto a target
└── deploy/      # the pipeline — render · apply · check · restore

# then reproduce it into the harness you use
$ python deploy/deploy.py apply --target claude
edit core/ render + adapt ~/.claude ~/.zcode …any harness

Two axes stay orthogonal: the harness (Claude Code, others) and the provider (the model behind it). The same blueprints deploy behind a Claude model today and a different model tomorrow, with no rewrite. The model is an engine you swap; the know-how is the same.

What's inside

Built for and around Claude Code

  • 19 hooks — token-economy, secret-leak guards, git safety, output hygiene, review gates.
  • Always-context rules — behavior, task-loop, session rules injected once per session.
  • Local-first memory — markdown files, wiki-linked, no external database to lose or migrate.
  • Skills, agents, commands — typed sub-agents where the harness supports them; the capability degrades gracefully where it doesn't.
  • ×3 review pipeline — unbiased fresh-context review with a PASS / NEEDS-FIXES / STOP verdict.
  • Idempotent, non-destructive deploy — collision-proof artifacts, namespaced merges, backups before any write.
source of truth
N
harness targets
19
hooks
0
runtime daemons

Who it's for

Made for people who run agents in production

Solo devs & small teams

Anyone driving an AI coding agent daily who wants it to stop forgetting, stop burning tokens, and follow a real lifecycle instead of vibes.

Teams standardising agents

One source of truth for rules, memory, skills and hooks across a codebase and across model providers — no per-machine drift, no vendor lock-in.

The engine behind our services

The same pipeline powers our managed Audit and Refactor offerings below — STC is both the open tool and the product engine.

Open core + services

Self-host the core. Or run it on your repo.

The engine is open source — install it from the public repository and run it yourself. On top of it we're building two managed, Claude-powered services that point the same review-and-refactor pipeline at your codebase.

Open source

STC Core

The full engine, AGPL-3.0. Self-install from the public repo and deploy it to your harness.

In development

Repo Audit

Point STC's fresh-context review pipeline — correctness, security, architecture — at any repository and get a ranked, verified findings report.

In development

Refactor

Automated, reviewed refactoring: deepen modules, cut coupling, raise testability — every change specced and verified before it lands.

The flywheel. Every audit enriches a shared library of checks, abuse-cases and defect patterns. The more repositories run through it, the more the pipeline catches — the product gets sharper with use.

Principles

Guiding constraints

Minimal third-party tools. Maximal use of the harness's own capabilities — native hooks, native imports, native sub-agents. No runtime daemon, no database, no framework.

One source of truth, many realisations. A capability is written once; each adapter declares how a harness realises it. You never edit the live harness directory by hand.

Non-destructive by construction. Collision-proof suffixes, namespaced JSON merges that refuse on genuine conflict, a backup before every write.

Degrade gracefully. A harness that lacks a native form keeps the capability — only the form is absent, never the know-how.