Borrowing it
Nothing to install: this file belongs to 3aKHP/prts-mcp. 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/3aKHP/prts-mcp/main/.agents/skills/comparative-evaluation/SKILL.mdgit clone --depth 1 https://github.com/3aKHP/prts-mcpWrote 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/3akhp/prts-mcp/comparative-evaluation)<a href="https://agentmods.dev/skills/3akhp/prts-mcp/comparative-evaluation"><img src="https://agentmods.dev/badge/skills/3akhp/prts-mcp/comparative-evaluation/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/3akhp/prts-mcp/comparative-evaluation"><img src="https://agentmods.dev/badge/skills/3akhp/prts-mcp/comparative-evaluation.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 | $0.00043 | $0.00392 |
| Opus 5.5 | $0.00017 | $0.00157 |
| Sonnet 5.5 | $0.00009 | $0.00078 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
comparative-evaluation 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 17d 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
Comparative evaluation
Use the repository's comparative evaluation guide as the public SOP and tools/experiments/experiment.py as the executor, relative to the repository root. This applies to quality and correctness metrics as well as performance.
Select the benchmark and measurement unit from the actual question. Fix the compared artifact identities, inputs, evaluator/runtime versions, metrics, guardrails, schedule and budgets before collecting measurements. Use output equivalence only when the benchmark requires it. Do not treat the offline description coverage demo as an Agent evaluation or an implementation of an upstream research benchmark.
Resolve the private environment via --profile, EXPERIMENT_PROFILE, or the plan's environment, in that order. Read the selected operations document with preview; use doctor before execution. For a fork without private configuration, init produces an offline local demo plus an operations manual. Remote templates require the contributor's own completed topology. Never infer a maintainer host, copy a private topology into tracked files, or treat ready=true as authorization.
Preserve frozen inputs and append-only attempts. Resume valid measurements without repeating them; explicit retries retain failed attempts and obey registered limits. Changes to the method or runtime need a new linked experiment. Inspect complete results, failures and guardrails before drawing a conclusion; report the scope and uncertainty supported by the data.
Use the allowlisted export for sharing, inspect its public identifiers, and keep raw logs and full archives private. Archive and verify evidence before owned cleanup. Follow the repository's normal PR and review workflow when promoting a change; this skill grants no additional execution, spending or merge authority.
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.
- 17d ago First seen · 17 lines · 43 tokens per session scan A fec0a17fcd9b
comparative-evaluation is a skill published in the GitHub repository 3aKHP/prts-mcp (15 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 392 once invoked, about $0.0002 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 2026-10-20.
comparative-evaluation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| comparative-evaluation3aKHP/prts-mcp | Skill | 15 | 3d ago | MIT | A | 43 | Codex |
| subagent-driven-developmentNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 17 | Claude Code, Codex |
| mcporterNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 16 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 43 | Claude Code, Codex |
| article-writingaffaan-m/ECC | Skill | 298k | 4d ago | MIT | A | 57 | Claude Code, Codex |
| safe-refactorJuliusBrussee/caveman | Skill | 118k | yesterday | Apache-2.0 | A | 29 | Claude Code, Codex |
| telegram-setupvellum-ai/vellum-assistant | Skill | 1.5k | 2d ago | MIT | A | 22 | Claude Code, Codex |