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 commands/einvoice-dev1/archsteer/xraygit clone --depth 1 https://github.com/einvoice-dev1/archsteerWhat 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 | $0.00024 | $0.00254 |
| Opus 5 | $0.00012 | $0.00127 |
| Sonnet 5 | $0.00005 | $0.00051 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
xray 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 2d 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 X-ray
Run archsteer xray in the repo root.
- If the command isn't found, install first:
pipx install archsteer(orpip install archsteer, needs Python 3.10+), or run one-off viauvx archsteer xray. - If this is the first run in the repo, it scaffolds
.archsteer/and writes.archsteer/architecture.md(living docs + a Mermaid layer diagram) and.archsteer/report.html.
Report back: component count, the detected layers, any architectural change(s)
since the last snapshot (the evolution feed), and point to the two generated
files. If .archsteer/architecture.yaml doesn't exist yet, mention that
archsteer init seeds a starter rule pack auto-matched to the repo's stack
(Java Spring, Salesforce, Python service, Next.js App Router, or Express→Next
migration) so conformance can be enforced going forward, not just observed.
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.
- 2d ago First seen · 22 lines · 24 tokens per session scan A 74940d226d8b
xray is a command published in the GitHub repository einvoice-dev1/archsteer (5 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 254 once invoked, about $0.0001 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 commands, from other repositories
adr-backfill
Audit code, documentation, and history for potential architecture decisions that were never recorded, then return a deduplicated evidence report. Read-only.
adr-draft
Draft one new ADR from a current decision or a selected backfill handoff. Writes a single new record, as proposed.
adr-check
Check the current change, or a plan, against the decisions that govern it and report a verdict per decision. Read-only.
adr-queue
Show the review queue — every decision still proposed, with its SLA state — so open questions are visible before they are planned around. Read-only.
adr-context
Load the architecture decisions that govern the paths you are about to change, before planning against them. Read-only.
check
Check a produced plan against the decisions that govern it. Read-only.