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/gulmezeren2-byte/erp-report-engineWrote 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/gulmezeren2-byte/erp-report-engine/trust-benchmark)<a href="https://agentmods.dev/commands/gulmezeren2-byte/erp-report-engine/trust-benchmark"><img src="https://agentmods.dev/badge/commands/gulmezeren2-byte/erp-report-engine/trust-benchmark/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/gulmezeren2-byte/erp-report-engine/trust-benchmark"><img src="https://agentmods.dev/badge/commands/gulmezeren2-byte/erp-report-engine/trust-benchmark.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 | $0.00029 | $0.00305 |
| Opus 5 | $0.00015 | $0.00152 |
| Sonnet 5 | $0.00006 | $0.00061 |
| Haiku 4.5 | $0.00003 | $0.00030 |
Grade A, and why
trust-benchmark 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 9d 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.
What it actually says
Run the trust benchmark for the erp-report-engine read-only SQL guard and explain what it proves.
Use the Bash tool to run it — it exercises the guard in memory, so no database or config is required:
uvx --from erp-report-engine erp-report-engine trust-benchmark
If uvx is not available, try pipx run erp-report-engine trust-benchmark, or erp-report-engine trust-benchmark if the package is already installed.
Then summarise for the user, concisely:
- How many of the 28 well-formed-SQL attacks the guard refused, and how many legitimate reads it allowed (it should be 28/28 and 8/8).
- The contrast the benchmark prints against the naive checks real tools ship — a starts-with-
SELECThead check (refuses only ~6/28) and a write-keyword blocklist (~9/28, and it even blocks a legitimate read whose string contains the word "delete"). The point: a guard that reads only a statement's shape lets file reads, shell calls and write-escapes through. - Invite them to paste their own attack into the live playground: https://gulmezeren2-byte.github.io/erp-report-engine/playground.html
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.
- 9d ago First seen · 19 lines · 29 tokens per session scan A 6f615a36625a
trust-benchmark is a command published in the GitHub repository gulmezeren2-byte/erp-report-engine (1 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 305 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 2026-08-31.
Other commands, from other repositories
playwright-test-heal
Run all my tests and fix the failing ones.
gan-build
Run a generator/evaluator build loop for implementation tasks with bounded iterations and scoring.
auto-verify
A command for checking a website's front-end user experience with Playwright, a tool that automates web browsers.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
ui-snapshot.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.