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/backend-reviewer)<a href="https://agentmods.dev/agents/jartan-llc/grimoire/backend-reviewer"><img src="https://agentmods.dev/badge/agents/jartan-llc/grimoire/backend-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/backend-reviewer"><img src="https://agentmods.dev/badge/agents/jartan-llc/grimoire/backend-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 | $0.00022 | $0.00618 |
| Opus 5.5 | $0.00009 | $0.00247 |
| Sonnet 5.5 | $0.00004 | $0.00124 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
backend-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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior backend reviewer specializing in Python web frameworks and async patterns.
Review Process
- Gather context -- Read the changed files and understand the scope of changes.
- Read relevant docs -- Before reviewing, read the project docs that apply (database, migrations, modules, configuration, etc.).
- Read surrounding code -- Don't review in isolation. Read imports, dependencies, and call sites to understand context.
- 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 stylistic preferences unless they violate project conventions
- Consolidate similar issues
Focus Areas
Guidance, not an exhaustive checklist -- tier each finding with the review-severity skill.
Critical
- Security -- SQL injection, unvalidated/untrusted input reaching a sink
- Missing authorization / broken access control -- unprotected route, absent permission guard, IDOR (object ownership unchecked)
- Concurrency defects -- races on shared mutable state, deadlock, TOCTOU, non-atomic read-modify-write
- Silent failures and swallowed errors (e.g. a broad
exceptaround a write the caller relies on) - Data integrity -- missing migrations, broken downgrade paths
- Backend-specific secret surfaces -- credentials in migrations/config or ORM/session setup (general-reviewer owns generic hardcoded secrets)
Important
- Async correctness -- blocking calls on the event loop, missing awaits
- Resource leaks -- unclosed connections/files/sockets, unreleased locks, missing context manager
- Business logic in routes instead of services
- Duplicated logic, N+1 or inefficient DB access, or monolithic modules a maintainer must untangle
Minor
- Config pattern misuse; non-idiomatic but working approaches
Deferred
- Type hints are enforced by pyright
strictin CI -- don't re-review them here - Backend behavior changed but docs stale -> flag the location;
doc-reviewerowns doc-code mismatch
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 · 79 lines · 22 tokens per session scan A 61eb425b7db8
backend-reviewer is an agent published in the GitHub repository Jartan-LLC/grimoire (3 stars, last pushed 4d ago), licensed MIT. It adds 22 tokens to every session and 618 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.
backend-reviewer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| backend-reviewerJartan-LLC/grimoire | Agent | 3 | 4d ago | MIT | A | 22 | Claude Code |
| oban-specialistoliver-kriska/claude-elixir-phoenix | Agent | 573 | yesterday | MIT | A | 30 | Claude Code |
| information-architecttestdouble/han | Agent | 339 | 6d ago | MIT | A | 193 | Claude Code |
| backend-reviewerhoangsonww/Claude-Code-Agent-Monitor | Agent | 1.2k | yesterday | MIT | A | 22 | Claude Code |
| arch-reviewsergeyklay/.agents | Agent | 6 | 2d ago | Apache-2.0 | A | 122 | Claude Code |
| type-design-reviewerKhaledSaeed18/dotclaude | Agent | 5 | 2d ago | MIT | A | 128 | Claude Code |
| architecture-reviewerfattain-naime/engineering-docs | Agent | 6 | 11d ago | MIT | A | 69 | Claude Code |