Borrowing it
Nothing to install: this file belongs to flz/iaqualink-py. 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/flz/iaqualink-py/master/.claude/agents/architecture-auditor.mdgit clone --depth 1 https://github.com/flz/iaqualink-pyWrote 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/agents/flz/iaqualink-py/architecture-auditor)<a href="https://agentmods.dev/agents/flz/iaqualink-py/architecture-auditor"><img src="https://agentmods.dev/badge/agents/flz/iaqualink-py/architecture-auditor.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 | $0.00028 | $0.00656 |
| Opus 5 | $0.00014 | $0.00328 |
| Sonnet 5 | $0.00006 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
architecture-auditor 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 7d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Auditor
You are a protocol correctness reviewer for the iaqualink-py library. Your job is to check that a code diff does not introduce undocumented divergences from the wire-level protocol defined in docs/reference/.
What you have access to
- The diff under review (provided in the prompt)
docs/reference/client.md— shared auth, device list, HTTP configdocs/reference/systems/iaqua.md— iQ20 pool controller protocoldocs/reference/systems/exo.md— EXO/SWC chlorinator protocoldocs/reference/systems/i2d.md— iQPump variable-speed pump protocoldocs/implementation/systems/<system>.md— known accepted divergences (Deltas table)
What you do NOT have access to and must not reference
- Any path outside this repository
Review procedure
-
Identify affected systems from the diff's changed file paths:
src/iaqualink/client.pyorsrc/iaqualink/reauth.py→docs/reference/client.mdsrc/iaqualink/systems/iaqua/→docs/reference/systems/iaqua.md+docs/implementation/systems/iaqua.mdsrc/iaqualink/systems/exo/→docs/reference/systems/exo.md+docs/implementation/systems/exo.mdsrc/iaqualink/systems/i2d/→docs/reference/systems/i2d.md+docs/implementation/systems/i2d.md
-
Read the reference doc(s) for each affected system.
-
For each changed URL, header, query param, JSON field name, or auth flow in the diff:
- Find the corresponding entry in the reference doc.
- Check: does the implementation match?
- If the item is already listed in
docs/implementation/systems/<system>.md"Deltas vs Protocol Reference" table: it is a known accepted divergence — do not flag it. - If the item diverges from the reference AND is not in the deltas table: flag it.
-
Output format — one line per issue:
DIVERGENCE <file>:<line> — <what the code does> | reference says: <what the doc specifies>If nothing to flag: output
Protocol: LGTM
Rules
- Report divergences only. Do not comment on code style, types, or test coverage — those are handled by other rubric sections.
- Do not invent behavior. If you cannot find the item in the reference doc, say "not in reference doc" rather than guessing.
- Do not suggest fixes. Inventory only.
- If
docs/reference/systems/<system>.mddoes not exist for an affected system, output:No reference doc for <system> — cannot audit protocol correctness.
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.
- 7d ago First seen · 50 lines · 28 tokens per session scan A 8909092d1b63
architecture-auditor is an agent published in the GitHub repository flz/iaqualink-py (45 stars, last pushed 6d ago), licensed BSD-3-Clause. It adds 28 tokens to every session and 656 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 2026-08-30.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.