Borrowing it
Nothing to install: this file belongs to tsz-org/tsz. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tsz-org/tsz/main/.agents/skills/tsz-architecture/SKILL.mdgit clone --depth 1 https://github.com/tsz-org/tszWrote 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/tsz-org/tsz/tsz-architecture)<a href="https://agentmods.dev/skills/tsz-org/tsz/tsz-architecture"><img src="https://agentmods.dev/badge/skills/tsz-org/tsz/tsz-architecture/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/tsz-org/tsz/tsz-architecture"><img src="https://agentmods.dev/badge/skills/tsz-org/tsz/tsz-architecture.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 | $0.00066 | $0.00520 |
| Opus 5.5 | $0.00026 | $0.00208 |
| Sonnet 5.5 | $0.00013 | $0.00104 |
| Haiku 4.5 | $0.00007 | $0.00052 |
Grade A, and why
tsz-architecture 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 23d 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
TSZ Architecture
Use for ownership-boundary work. Default direction: solver-first semantics, thin checker, syntax parser, symbol/flow binder, output-only emitter.
Rules
- Read
AGENTS.mdanddocs/plan/ROADMAP.mdfor conformance, emit, performance, architecture, LSP/WASM, Sound Mode, or DRY cleanup work. - Inspect overlapping PRs/issues.
- State:
When <structural condition>, tsc does X; tsz does X through <owner>. - No fixture paths, user names, source snippets, rendered strings, or single test names as decision inputs.
- Prefer one query/boundary helper over local checker branches.
Owners
- Scanner: tokens and interning.
- Parser: syntax-only AST.
- Binder: symbols, scopes, hoisting, flow graph.
- Solver: relations, evaluation, inference, instantiation, operations, narrowing, semantic caches.
- Checker: orchestration, diagnostics, source spans.
- Emitter: JS/DTS output and transform scheduling.
- LSP/WASM/CLI: API consumers.
Boundary Workflow
- Classify as
WHAT(solver/query boundary) orWHERE(checker location/ diagnostic orchestration). - Search existing boundaries:
rg "struct .*Request|RelationRequest|query_boundaries|TypeData" crates/tsz-checker/src crates/tsz-solver/src - Put checker-facing semantic adapters under
crates/tsz-checker/src/query_boundaries/. - Avoid new checker
TypeKeymatching, directCompatChecker, raw interning, or type-shape recursion. - Add owning-crate tests and adjacent cases varying names/wrappers.
Guards
python3 scripts/arch/arch_guard.py
scripts/arch/check-checker-boundaries.sh
python3 scripts/arch/test_arch_guard.py
Use targeted cargo nextest run; wrap heavy runs with scripts/safe-run.sh.
PR notes: structural rule, owner layer, adjacent matrix, guard/tests, temporary debt/removal condition.
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.
- 23d ago First seen · 56 lines · 66 tokens per session scan A 36e9db5b06f9
tsz-architecture is a skill published in the GitHub repository tsz-org/tsz (577 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 520 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-28.
Other skills, from other repositories
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
review
Diff-scoped correctness review that reads the codebase around the change — callers, contracts, and invariants — and returns line-anchored findings ranked by severity with confidence, then a merge-risk verdict. Use for reviewing a PR, diff, or named change set. Not for style review, approvals-as-rubber-stamp, or…
code-review
Run a final code review on a pull request.
code-breaking-changes
Search for breaking changes in external integration surfaces.
tuicr
Use tuicr's review CLI to read and add comments in active TUI review sessions, and launch tuicr in cmux, tmux, Zellij, or Herdr when a user needs an interactive review pane.
architecture-audit
Systematic architecture audit and refactoring methodology for Rust + TypeScript codebases. Use when performing refactoring, cleanup, unification, code review, dead code removal, module reorganization, or tech debt elimination. Ensures no naming confusion, semantic overloading, hidden defaults, duplicate logic, or…