Borrowing it
Nothing to install: this file belongs to elbruno/ElBruno.MempalaceNet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/elbruno/ElBruno.MempalaceNet/main/.squad/skills/benchmark-parity-triage/SKILL.mdgit clone --depth 1 https://github.com/elbruno/ElBruno.MempalaceNetWrote 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/elbruno/elbruno.mempalacenet/benchmark-parity-triage)<a href="https://agentmods.dev/skills/elbruno/elbruno.mempalacenet/benchmark-parity-triage"><img src="https://agentmods.dev/badge/skills/elbruno/elbruno.mempalacenet/benchmark-parity-triage/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/elbruno/elbruno.mempalacenet/benchmark-parity-triage"><img src="https://agentmods.dev/badge/skills/elbruno/elbruno.mempalacenet/benchmark-parity-triage.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 | $0.00000 | $0.00227 |
| Opus 5 | $0.00000 | $0.00113 |
| Sonnet 5 | $0.00000 | $0.00045 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
benchmark-parity-triage 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 12d 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
Benchmark Parity Triage
When to use
Use this when a benchmark harness exists but parity with an upstream reference implementation is unproven.
Steps
- Run the repo's existing smoke/control benchmark first to prove the harness still executes.
- Locate the upstream documented dataset source and fetch the real dataset without committing large artifacts.
- Attempt the benchmark with the real dataset exactly as documented.
- Compare three things before trusting any score:
- dataset shape (JSON vs JSONL, field names, nesting),
- runtime embedder/model (real model vs deterministic/mock embedder),
- benchmark semantics (shared corpus vs fresh corpus per query, same top-k, same scoring).
- If the full run is blocked, codify the blocker in tests/docs with the exact failure mode and command line used.
Pattern
Synthetic smoke data can prove the harness works while still hiding parity blockers. The fastest honest QA path is: control run succeeds, real-data run fails, document the first concrete incompatibility, then list any deeper semantic mismatches found in code review.
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.
- 12d ago First seen · 22 lines · 0 tokens per session scan A f1aeb1b0ef93
benchmark-parity-triage is a skill published in the GitHub repository elbruno/ElBruno.MempalaceNet (11 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 227 tokens. 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 2026-08-30.
Other skills, from other repositories
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
potpie-project-preferences
Use before writing, modifying, reviewing, refactoring, or testing code so repo/project preferences surface: error handling, file structure, frameworks, logging, dependency choices, testing, security, API style, and naming. Also use after code work when a reusable project preference should be recorded.
tla
TLA+ formal verification — extracts invariants, models state machines, checks for race conditions. Use after browser tests or manually. Triggers: verify, formal, invariant, TLA, race condition.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
skill-release-gate
Evaluate an Agent Skill bundle for structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability before release.