AGENTS.agentops-evaluation

AGENTS.agentops-evaluation is an agent for coding agents from jeremylongworth-source/AgentSkills. It costs 0 tokens per session (275 once invoked), scanned A, original, MIT.

A set of local instructions for evaluating coding-agent add-ons, such as skills and skill bundles. It helps route evaluation tasks to the appropriate method.

In plain words
What is it for?
Evaluating skill quality, writing test scenarios, comparing agent results before and after a change, mapping acceptance criteria, checking prompt regressions, scoring outputs, and reviewing added token or tool overhead.
Why use it?
It replaces ad hoc judgments with repeatable checks, comparisons, scoring, and evidence. This makes it easier to decide whether an add-on should be kept, changed, combined, postponed, or retired.

Agent

Install

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.

agentmods
npx agentmods add agents/jeremylongworth-source/agentskills/agents.agentops-evaluation
Clone the repo
git clone --depth 1 https://github.com/jeremylongworth-source/AgentSkills

Wrote 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.

agentmods badge for AGENTS.agentops-evaluation

README.md
[![agentmods](https://agentmods.dev/badge/agents/jeremylongworth-source/agentskills/agents.agentops-evaluation.svg)](https://agentmods.dev/agents/jeremylongworth-source/agentskills/agents.agentops-evaluation)
Your own site
<a href="https://agentmods.dev/agents/jeremylongworth-source/agentskills/agents.agentops-evaluation"><img src="https://agentmods.dev/badge/agents/jeremylongworth-source/agentskills/agents.agentops-evaluation.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 275 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00275
Opus 5 $0.00000 $0.00138
Sonnet 5 $0.00000 $0.00055
Haiku 4.5 $0.00000 $0.00028

Measured 4d ago against content hash 38b882698814, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AGENTS.agentops-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 4d 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.

agents/AGENTS.agentops-evaluation.md · 31 lines

What it actually says

Use local skills as the primary routing layer for AgentOps evaluation work.

Use skill-benchmark-design when defining whether a skill or bundle improves outputs and what evidence should be captured.

Use scenario-test-authoring when adding route scenarios, expected routing, or scenario coverage for a skillset.

Use before-after-evaluation when comparing baseline and skill-enabled agent outputs and making a keep/revise/split/merge/defer/retire decision.

Use acceptance-criteria-mapper when turning skill, bundle, feature, or workflow goals into observable pass/fail checks.

Use prompt-regression-testing when creating reusable prompt tests for known skill behaviors, failures, or safety boundaries.

Use skill-output-scoring when scoring outputs with a rubric and documenting evidence for each score.

Use skill-token-overhead-review when reviewing context, token, tool, or process overhead added by a skill or bundle.

Use skill-evaluation-iteration for broader skill improvement loops and concise-technical-writing for reports, decisions, and release notes.

Keep evaluations vendor-neutral. Do not require a specific tracing, observability, or LLM-judge platform unless the user explicitly chooses one. Do not publish private prompts, customer data, secrets, or sensitive outputs in public evaluation artifacts.

Changes

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.

  1. 4d ago First seen · 31 lines · 0 tokens per session scan A 38b882698814

Subscribe to this mod's changes

AGENTS.agentops-evaluation is an agent published in the GitHub repository jeremylongworth-source/AgentSkills (1 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 275 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 2026-08-31.