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.
git 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/commands/einvoice-dev1/archsteer/check)<a href="https://agentmods.dev/commands/einvoice-dev1/archsteer/check"><img src="https://agentmods.dev/badge/commands/einvoice-dev1/archsteer/check/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/commands/einvoice-dev1/archsteer/check"><img src="https://agentmods.dev/badge/commands/einvoice-dev1/archsteer/check.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 | $0.00024 | $0.00200 |
| Opus 5.5 | $0.00010 | $0.00080 |
| Sonnet 5.5 | $0.00005 | $0.00040 |
| Haiku 4.5 | $0.00002 | $0.00020 |
Grade A, and why
check 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 1mo 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
ArchSteer check
Run archsteer check in the repo root.
- Requires
.archsteer/architecture.yamlto exist (runarchsteer initfirst if not — it auto-detects the stack and seeds a starter rule pack). - Only NET-NEW error-severity violations against the repo's baseline block (exit code 1); pre-existing debt never blocks. The output includes a conformance-score line (percent + delta since the last snapshot).
If it fails, list the net-new violations shown (file, rule, message) and fix
the ones caused by the current change before finishing. If a violation looks
like a genuine, repo-wide pattern shift rather than a one-off, suggest running
archsteer adr instead of just patching around it.
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.
- 1mo ago First seen · 19 lines · 24 tokens per session scan A 00a68a0babf2
check is a command published in the GitHub repository einvoice-dev1/archsteer (5 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 200 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
adr-check
Check the current change, or a plan, against the decisions that govern it and report a verdict per decision. Read-only.
comply
Check a plan's or diff's compliance with this repo's rule files — deterministic selection, one starved brief per rule, verdicts re-checked against the plan.
audit
Audit the premises of a document — refute-first, one claim per agent, refutations returned as checkable anchors.
ground
Verify the Evidence Anchors in a document (defaults to the newest plan file).
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
conformance
Assess architecture conformance — ADR decision implementation, cross-decision consistency, design-principles alignment, architecture drift, technical debt, and custom constraint rules.