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.
npx skills add Utkarsh-Sinha0/razor-dvara --skill razor-dvara-evalsgit clone --depth 1 https://github.com/Utkarsh-Sinha0/razor-dvaraWrote 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/skills/utkarsh-sinha0/razor-dvara/razor-dvara-evals)<a href="https://agentmods.dev/skills/utkarsh-sinha0/razor-dvara/razor-dvara-evals"><img src="https://agentmods.dev/badge/skills/utkarsh-sinha0/razor-dvara/razor-dvara-evals/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/skills/utkarsh-sinha0/razor-dvara/razor-dvara-evals"><img src="https://agentmods.dev/badge/skills/utkarsh-sinha0/razor-dvara/razor-dvara-evals.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 | $0.00040 | $0.00388 |
| Opus 5 | $0.00020 | $0.00194 |
| Sonnet 5 | $0.00008 | $0.00078 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
razor-dvara-evals 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 10d 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
Razor Dvara Eval Runner
Triggers
- "run the evals"
- "show me the batch results"
- "validate the gate decisions"
- "generate eval report"
Body
- Run
pnpm vitest run evals/results.test.tsto verify the harness is deterministic. - Run the batch runner programmatically (or via a script) to produce the full results object.
- Format results using
evals/report.tsfor human-readable output. - Review the exceptions list — every exception is a scenario where the gate decision didn't match the expected outcome. These are the honest gaps.
- Cross-reference the assumptions file (
evals/assumptions.ts) to confirm every rate has a source citation.
Output shape
Total orders: 50
Allowed: 12 | Fee applied: 18 | Partial prepay: 8 | Blocked: 12
Simulated ₹ protected: ₹14,200
False positives (safe orders blocked): 3
Exceptions: 3 (listed below)
EXCEPTIONS:
- scenario_042: expected allow, got blocked (GATE_NOT_CONFIGURED)
- scenario_047: expected fee_applied, got partial_prepay
- scenario_049: expected blocked, got allow (rule precedence issue)
ASSUMPTIONS USED:
- Baseline COD RTO: 26% (Shipway FY25, vendor)
- Tier-2/3 COD RTO: 30% (bepragma Jun 2026, vendor)
- High-value lift: +5% (Nitro Commerce Mar 2026)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 42 lines · 40 tokens per session scan A b2e48eacdadf
razor-dvara-evals is a skill published in the GitHub repository Utkarsh-Sinha0/razor-dvara (0 stars, last pushed 20d ago), licensed MIT. It adds 40 tokens to every session and 388 once invoked, about $0.0002 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 skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.