What is agent-eval-framework?

A framework for testing AI agents with scoring rules, checks and comparisons against reference answers. It measures areas such as correctness, completeness, relevance, safety and code quality.

Use it before deploying an agent, after changing its instructions, when quality appears to drop, during regular reviews or when comparing agent configurations.

It makes output quality easier to review consistently instead of relying only on informal judgement. It can reveal declines in quality after prompts or skills change.

agent-eval-framework — Skill by BuilderCed

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 skills/builderced/agent-skills/agent-eval-framework

Any agent

npx skills add BuilderCed/agent-skills --skill agent-eval-framework

Clone the repo

git clone --depth 1 https://github.com/BuilderCed/agent-skills

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,163 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.

Model	Per session	Once invoked
Fable 5	$0.00026	$0.01163
Opus 5	$0.00013	$0.00581
Sonnet 5	$0.00005	$0.00233
Haiku 4.5	$0.00003	$0.00116

Measured yesterday against content hash e31186f6616d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-eval-framework 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 yesterday.

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.

skills/eval/agent-eval-framework/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Evaluation Framework

When to Use

Before deploying an agent to production
After changing an agent's system prompt or skills
When agent output quality seems to degrade
During periodic quality reviews
When comparing two agent configurations

Step 1: Define Evaluation Criteria

Choose criteria relevant to your agent's purpose:

Universal Criteria

Criterion	Question	Score
Correctness	Is the output factually/technically correct?	0-10
Completeness	Does it cover all required aspects?	0-10
Relevance	Is every part relevant to the request?	0-10
Safety	Does it avoid harmful/insecure patterns?	0-10

Code-Specific Criteria

Criterion	Question	Score
Functionality	Does the code work as intended?	0-10
Edge Cases	Are edge cases handled?	0-10
Style	Does it match project conventions?	0-10
Security	Are there vulnerabilities?	0-10

Content-Specific Criteria

Criterion	Question	Score
Accuracy	Are claims supported by evidence?	0-10
Tone	Does it match the intended audience?	0-10
Structure	Is it well-organized?	0-10
Originality	Does it avoid generic/cliche content?	0-10

Step 2: Choose Evaluation Method

A. Assertion-Based (Automated)

Define pass/fail conditions:

ASSERT: output contains "disclaimer"
ASSERT: output does NOT contain "TODO"
ASSERT: code compiles without errors
ASSERT: response length < 2000 tokens
ASSERT: no PII detected in output

Best for: Regression testing, CI/CD pipelines.

B. Reference-Based (Semi-Automated)

Compare output against a known-good reference:

Exact match (strict)
Semantic similarity (using embeddings)
Key-point coverage (checklist)

Best for: Consistent tasks with known expected outputs.

C. Rubric-Based (Human + AI)

Score each criterion 0-10 with justification:

Correctness: 8/10 — Accurate but missed one edge case
Completeness: 7/10 — Covered 5 of 6 required points
Safety: 10/10 — No security issues
TOTAL: 25/30 (83%) — PASS (threshold: 70%)

Best for: Complex, subjective outputs.

Read the full file on GitHub · 158 lines

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.

yesterday First seen · 158 lines · 26 tokens per session scan A e31186f6616d

Subscribe to this mod's changes

agent-eval-framework is a skill published in the GitHub repository BuilderCed/agent-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 1,163 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.

Code review Testing africa agent-skills ai-act ai-agents claude-code codex eval

agent-eval-framework