What it does
The skill audits a codebase and links each claim the repository makes about itself to a mechanism that fails when the claim stops being true, such as a compiler, linter, automated tests or review. It applies nine principles from Context Architecture: structure that states what the system does, AGENTS.md files placed at module boundaries, codified conventions, and checks on every self-description.
It is suited to repositories where agents reimplement existing code, invent structure, follow stale or deleted documentation, propagate deprecated patterns, or resolve ambiguity inconsistently. It also fits requests to make a repository agent-ready or AI-legible, or to add or fix AGENTS.md or CLAUDE.md files. It covers new repositories built to be legible from the start and existing ones restructured in steps. Related terms in the source include harness engineering, context files, instruction bloat, cognitive debt and agent readiness.
The source describes the approach but gives no setup steps for the skill itself. It is published under the CC-BY-4.0 license.
Limitations and requirements
The approach assumes the repository already has, or will add, a compiler, linter, automated tests or review process to enforce each claim.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 18 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 36
context-architecture
Audit a codebase and bind every claim it makes about itself to a mechanism that fails when the claim stops being true, so it is legible to people and AI agents. Applies Context Architecture's nine principles: make structure say what the system does, place AGENTS.md at boundaries, codify conventions, and bind every claim the repo makes about itself to a mechanism (compiler, linter, automated tests, review) that fails when the claim stops being true. Works greenfield (a repo born legible) and brownfield (a repo restructured in steps). Use when an agent reimplements code that already exists, inve
v0.3.0As shown on www.aitmpl.com when we last read it