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/infraspecdev/tesseractWrote 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/commands/infraspecdev/tesseract/review-backend)<a href="https://agentmods.dev/commands/infraspecdev/tesseract/review-backend"><img src="https://agentmods.dev/badge/commands/infraspecdev/tesseract/review-backend/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/commands/infraspecdev/tesseract/review-backend"><img src="https://agentmods.dev/badge/commands/infraspecdev/tesseract/review-backend.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 | $0.00023 | $0.01021 |
| Opus 5.5 | $0.00009 | $0.00408 |
| Sonnet 5.5 | $0.00005 | $0.00204 |
| Haiku 4.5 | $0.00002 | $0.00102 |
Grade A, and why
review-backend 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 1mo 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Backend
Run a focused backend code review. Detects the stack (Java/Kotlin, Python, Node/TS, Go) from repo markers, loads agnostic and framework-specific skills under shield/skills/backend/, and dispatches cross-cutting concerns to specialist agents.
Usage
/review-backend [path or scope] [--full]
/review-backend(no arg, on a branch) — review changed files vsmain/review-backend services/api/— review a specific subtree/review-backend --fullor/review-backend .— review the whole repo (excluding the default exclude list)
Paths
Writes registry-tracked paths under {review_dir} = {output_dir}/{feature}/reviews/code/{date}{_counter} (review_type=code; primary agent=backend-engineer, with additional specialists writing their own {review_detailed} entries). See shield/schema/output-paths.yaml and the counter-resolution rule in /review. changes.md is a side-artifact (applied-fixes log, not in registry).
Output Path — MANDATORY
First, find the project root by locating .shield.json (check current directory, then parent directories). Read .shield.json to get output_dir (default: docs/shield). Determine {feature} (current feature directory name; if none exists yet, derive from current branch or story context + -YYYYMMDD). Resolve {date}{_counter} per the counter rule in /review (today's ISO date in YYYY-MM-DD format; empty _counter for first same-day run, _2/_3/... otherwise).
Write findings under {review_dir} = {output_dir}/{feature}/reviews/code/{date}{_counter}/:
{review_dir}/
├── summary.md ← {review_summary}
├── changes.md ← applied-fixes log (side-artifact)
└── detailed/
├── backend-engineer.md ← {review_detailed} (agent=backend-engineer)
└── <specialist>.md ← {review_detailed} (one per dispatched specialist)
Numbered run subfolders (code-review/{N}-{slug}/) are gone — runs are date-keyed and never overwrite.
Replace {project_root} with the absolute path to the directory containing .shield.json.
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.
- 1mo ago First seen · 73 lines · 23 tokens per session scan A f0fa1fa232cc
review-backend is a command published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 1,021 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 2026-09-03.
Other commands, from other repositories
evaluate-connector
Evaluate a Fivetran connector for correctness, SDK compliance, security, and reliability.
review-rust
Focused Rust/Tauri backend review with rust-backend-architect (Primary Owner).
document
On-demand documentation generation — API docs, architecture updates, user guides.
connector-review
Review DataHub connector code for standards compliance and quality.
api-review
Review the current code or API against API design principles — identifies violations and suggests improvements.
api-style-review
Review SAP API style compliance for REST, OData, OpenAPI, SDK naming, documentation, and lifecycle readiness.