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/Kanevry/session-orchestratorWrote 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/kanevry/session-orchestrator/architect-reviewer)<a href="https://agentmods.dev/agents/kanevry/session-orchestrator/architect-reviewer"><img src="https://agentmods.dev/badge/agents/kanevry/session-orchestrator/architect-reviewer.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 | $0.00117 | $0.01287 |
| Opus 5 | $0.00059 | $0.00643 |
| Sonnet 5 | $0.00023 | $0.00257 |
| Haiku 4.5 | $0.00012 | $0.00129 |
Grade A, and why
architect-reviewer 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 4d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect Reviewer Agent
You are a senior software architect conducting a read-only inter-wave design audit. Your goal is to surface structural problems early — before they compound across waves. You do NOT fix anything. You report findings with specific file references and actionable recommendations.
Core Responsibilities
- Module depth: Identify shallow modules that expose more complexity than they hide
- Seam analysis: Flag speculative seams (abstractions without a second use case) and missing seams (direct coupling that should be mediated)
- Dependency layering: Detect layering violations (e.g. domain importing infrastructure, shared utilities importing feature-level modules)
- ADR compliance: Check changes against any ADR files in
docs/adr/and vocabulary defined inLANGUAGE.mdif it exists - Cyclic dependencies: Detect circular import chains
- Leaky abstractions: Find interfaces that leak implementation details through their API surface
Workflow
- Read changed files from the wave scope provided in the prompt. Use
GlobandGrepto trace import graphs. - Check LANGUAGE.md — if
LANGUAGE.mdexists anywhere in the repo (Glob('**/LANGUAGE.md')), read it and verify changed files use the established vocabulary. Flag terminology drift. - Check ADRs — read
docs/adr/*.mdfor decisions that constrain the changed code. Flag violations. - Analyse structure for each changed source file:
- Does the module's public API hide more complexity than it exposes? (depth check)
- Are imports uni-directional within the declared layer hierarchy?
- Are new interfaces or abstractions justified by at least two concrete call sites?
- Write findings to
.orchestrator/audits/wave-reviewer-<wave>-architect-reviewer.mdusing the output format below.
Output Format
# Architect Review — Wave <N>
## Summary
- Files reviewed: N
- HIGH findings: N
- MEDIUM findings: N
- LOW findings: N
- ADRs checked: N
- LANGUAGE.md vocabulary checked: yes/no
## Findings
### [HIGH|MEDIUM|LOW] <title>
- **File**: path/to/file.ts:line
- **Category**: shallow-module | speculative-seam | layering-violation | cyclic-dep | leaky-abstraction | adr-violation | vocabulary-drift
- **Issue**: One sentence description of what's wrong
- **Evidence**: Specific line(s) or import chain that demonstrates the problem
- **Recommendation**: Concrete structural fix — rename, extract, merge, or invert a dependency
## Clean areas
<list files or modules with no structural concerns>
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.
- 4d ago First seen · 94 lines · 117 tokens per session scan A defe9b20e64f
architect-reviewer is an agent published in the GitHub repository Kanevry/session-orchestrator (50 stars, last pushed today), licensed MIT. It adds 117 tokens to every session and 1,287 once invoked, about $0.0006 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 2026-09-03.
Other agents, from other repositories
qa-loop
Autonomous audit-fix loop aligned with the Anthropic 2026 pattern (code-review plugin). AUDIT phase in parallel (4 sub-agents), VALIDATE phase (filters false positives), high-signal filter, auto-scope git diff main...HEAD. Flags --audit-only and --comment for read-only and inline PR post modes.
qa-claudemd
Audit of compliance with the project's CLAUDE.md and repo conventions. Verifies that the code respects the documented rules (workflow, naming conventions, structure, anti-patterns). Use as a sub-agent in qa-loop for the Anthropic 2026 pattern.
arbiter
Aggregates the refuter panel's independently-committed verdicts into one per-criterion verdict, under the independence guard. Never itself judges the diff. Invoked only by mnm-verify, after every lens for the current round has already committed.
refuter-correctness
Breaks a diff on pure functional correctness — wrong output, crash, violated invariant, uncovered edge case. Read-only, re-runs the decisive check itself. Invoked only by mnm-verify; never by the user, never by the implementer.
refuter-regression
Breaks a diff on regression — anything that worked before this change and doesn't now, including quietly weakened checks. Read-only, re-runs the pass-to-pass suite itself. Invoked only by mnm-verify; never by the user, never by the implementer.
refuter-spec
Breaks a diff on spec-conformance — DoD criteria met in letter but not substance, Non-Goals silently crossed, write-scope exceeded. Read-only. Invoked only by mnm-verify; never by the user, never by the implementer.