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 skills/einvoice-dev1/archsteer/architecture-governancenpx skills add einvoice-dev1/archsteer --skill architecture-governancegit clone --depth 1 https://github.com/einvoice-dev1/archsteerWrote 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/einvoice-dev1/archsteer/architecture-governance)<a href="https://agentmods.dev/skills/einvoice-dev1/archsteer/architecture-governance"><img src="https://agentmods.dev/badge/skills/einvoice-dev1/archsteer/architecture-governance.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.01012 |
| Opus 5 | $0.00036 | $0.00506 |
| Sonnet 5 | $0.00015 | $0.00202 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade A, and why
architecture-governance 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture governance with ArchSteer
ArchSteer derives a repo's real architecture from source (components, layers, dependencies, data access, external calls) and — once a target is declared — enforces it as fitness functions with a net-new ratchet: only NEW violations block, existing debt never freezes feature work.
Is it set up in this repo?
Check for .archsteer/model.json. If it's missing, this repo hasn't been
mapped yet:
archsteer xray # zero-config: map + living docs + evolution feed, no rules required
If .archsteer/architecture.yaml doesn't exist either, the repo has never
declared a target:
archsteer init # auto-detects the stack, seeds a matching starter rule pack + ADRs
If neither archsteer nor uvx is on PATH, install with pipx install archsteer
or pip install archsteer (needs Python 3.10+), or run one-off via uvx archsteer <command>.
When to use it during a task
Starting work in an unfamiliar repo — run archsteer xray (or, if the MCP
server is connected, call current_architecture) to see real component/layer
counts and the current conformance score before making assumptions about
structure from a partial read of the code.
Before writing or editing a file that touches an architectural boundary
(new dependency, new data-access call, new external/third-party call, a file
in a layer you haven't touched yet) — call the get_target_pattern MCP tool
with that file path (or read .archsteer/architecture.yaml directly) to see
which declared rules apply, and follow the steer directive on each one
instead of copying whatever an adjacent legacy file happens to do.
After editing a file — call the check_file MCP tool with that file path
(or run archsteer check) to verify the edit didn't introduce a violation,
without waiting for CI to say so.
Before finishing/committing an architecturally significant change — run
archsteer check. It fails only on NET-NEW error-severity violations against
the repo's baseline; pre-existing debt is never a blocker. If a repo has
archsteer install-hooks set up, this already runs automatically on git push.
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.
- 5d ago First seen · 88 lines · 73 tokens per session scan A 5e4eeabf447d
architecture-governance is a skill published in the GitHub repository einvoice-dev1/archsteer (5 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,012 once invoked, about $0.0004 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 skills, from other repositories
architecture-paradigms
Selects and routes to the right architecture paradigm. Use when choosing patterns for a new system or comparing trade-offs before making architecture decisions.
system-design-patterns
Architecture patterns (monolith, microservices, CQRS, event-driven, api-gateway, scalability), ADR methodology, trade-off analysis, fitness functions, and deterministic ADR completeness scoring via executable script. Use proactively when making or reviewing significant architectural decisions, writing or auditing…
decision-backfill
Use when auditing an existing codebase, documentation set, plans, RFCs, or git history for architecture decisions that were made but never recorded as ADRs, and when triaging potential records before drafting them.
decision-memory
Use when planning, designing, reviewing, or changing code in a repository that keeps ADRs (usually docs/adr) — to load the decisions that already govern the work, check a plan or diff against them, or record a new decision. Also use when a choice feels already-settled and you cannot find where it was settled.
code-review
Review pull requests in adrkit for actionable defects and conflicts with governing architecture decisions. Use during Copilot code review to inspect changed paths, retrieve relevant ADR context through the adrkit MCP server, and produce evidence-backed inline findings.
plan
Structured technical planning before implementation — architecture and task breakdown.