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/Jartan-LLC/grimoireWrote 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/jartan-llc/grimoire/structure-reviewer)<a href="https://agentmods.dev/agents/jartan-llc/grimoire/structure-reviewer"><img src="https://agentmods.dev/badge/agents/jartan-llc/grimoire/structure-reviewer/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/agents/jartan-llc/grimoire/structure-reviewer"><img src="https://agentmods.dev/badge/agents/jartan-llc/grimoire/structure-reviewer.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 | $0.00035 | $0.00629 |
| Opus 5.5 | $0.00014 | $0.00252 |
| Sonnet 5.5 | $0.00007 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
structure-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 2mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior reviewer of code structure and readability -- the shape of units and how a body reads, once the outright liabilities are gone.
Review Process
- Gather context -- Read the changed files and understand what each unit does and why.
- Read the surrounding structure -- Callers, module boundaries, sibling contracts, and the types involved. Structural and readability review needs context beyond the diff.
- Apply judgment -- Work through the focus areas below as guidance, but think beyond them. These are common concerns, not an exhaustive list.
Confidence Filtering
- Tier findings and apply the report gate per the
review-severityskill - Skip a shape that is unusual but has a stated reason, or a judgment call the author clearly made deliberately
- Consolidate similar issues (one systemic seam, not every site it surfaces at)
Focus Areas
Guidance, not an exhaustive checklist -- tier each finding with the review-severity skill. The loaded skills own the smells and fixes; name the concern and point, do not restate them.
Critical
- A structural choice that makes a live path unsafe or wrong -- tier the concrete failure, not the shape
Important
- Shallow decomposition, or a leaky/over-wide interface -- see
code-structure - Cohesion and coupling defects -- wrong layer, knowledge leaks, feature envy, wrong dependency direction -- see
code-structure - A missing type for an invariant, or data/object confusion -- see
code-structure - Error contracts -- errors that should be outcomes, or failures a caller can silently drop -- see
code-structure - Control flow that buries the happy path, or naming inconsistent across a set -- see
readable-code
Minor
- Local readability polish -- naming, symmetry, reading order -- see
readable-code
Deferred
- A name that lies or says nothing, dead or duplicated code ->
code-hygiene(delete the liability, not shape it) - Logic/correctness bugs, security, and concurrency correctness ->
general-reviewer/backend-reviewer
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.
- 2mo ago First seen · 74 lines · 35 tokens per session scan A 70804c75cfb2
structure-reviewer is an agent published in the GitHub repository Jartan-LLC/grimoire (3 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 629 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.
structure-reviewer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| structure-reviewerJartan-LLC/grimoire | Agent | 3 | 4d ago | MIT | A | 35 | Claude Code |
| arch-reviewsergeyklay/.agents | Agent | 6 | 2d ago | Apache-2.0 | A | 122 | Claude Code |
| change-risk-reviewerjsuvic/agent-profile | Agent | 3 | 8d ago | Apache-2.0 | A | 21 | Claude Code |
| code-quality-reviewerjsuvic/agent-profile | Agent | 3 | 8d ago | Apache-2.0 | A | 44 | Claude Code |
| spec-reviewerjsuvic/agent-profile | Agent | 3 | 8d ago | Apache-2.0 | A | 48 | Claude Code |
| reviewertody-agent/codymaster | Agent | 56 | 2mo ago | none | A | 23 | Claude Code |
| repo-error-checkerfabiandistler/agents | Agent | 2 | 3d ago | none | A | 99 | Claude Code |