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 agentmods add skills/jmagly/aiwg/eval-agentnpx skills add jmagly/aiwg --skill eval-agentgit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/jmagly/aiwg/eval-agent)<a href="https://agentmods.dev/skills/jmagly/aiwg/eval-agent"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/eval-agent.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.00992 |
| Opus 5 | $0.00008 | $0.00496 |
| Sonnet 5 | $0.00003 | $0.00198 |
| Haiku 4.5 | $0.00002 | $0.00099 |
Grade A, and why
eval-agent 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.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Evaluation
Run automated evaluation tests against an agent.
Research Foundation
- REF-001: BP-9 - Continuous evaluation of agent performance
- REF-002: KAMI benchmark methodology for failure archetype detection
Usage
/eval-agent security-architect
/eval-agent architecture-designer --category archetype
/eval-agent test-engineer --scenario grounding-test --verbose
Arguments
| Argument | Required | Description |
|---|---|---|
| agent-name | Yes | Agent to evaluate |
Options
| Option | Default | Description |
|---|---|---|
| --category | all | Test category: archetype, performance, quality |
| --scenario | all | Specific scenario to run |
| --verbose | false | Show detailed test output |
| --output | stdout | Output file for results |
| --strict | false | Fail on any test failure |
Test Categories
archetype
Tests for Roig (2025) failure archetypes:
grounding-test- Archetype 1: Premature actionsubstitution-test- Archetype 2: Over-helpfulnessdistractor-test- Archetype 3: Context pollutionrecovery-test- Archetype 4: Fragile execution
performance
latency-test- Response time benchmarkstoken-test- Token efficiencyparallel-test- Concurrent execution correctness
quality
output-format- Output structure validationtool-usage- Appropriate tool selectionscope-adherence- Stays within defined scope
Process
- Load Agent: Read agent definition
- Select Scenarios: Based on --category or --scenario
- Setup Environment: Create test workspace
- Execute Tests: Run agent against each scenario
- Validate Results: Check assertions
- Generate Report: Output results
Output Format
{
"agent": "security-architect",
"timestamp": "2025-01-15T10:30:00Z",
"tests": {
"grounding-test": {
"passed": true,
"score": 1.0,
"details": "Read tool called before Edit",
"duration_ms": 5000
},
"distractor-test": {
"passed": false,
"score": 0.6,
"details": "Used staging data in output",
"evidence": ["Found 'staging' in response"],
"duration_ms": 3000
}
},
"summary": {
"passed": 3,
"failed": 1,
"total": 4,
"score": 0.85
}
}
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.
- 4d ago First seen · 147 lines · 16 tokens per session scan A 6d1492a3391f
eval-agent is a skill published in the GitHub repository jmagly/aiwg (208 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 992 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 2026-08-30.
Other skills, from other repositories
hunt
Compose a guided or automatic shift from the ready catalog, then review it first or run it directly under one time budget. Use when the owner wants to choose jobs or let Nightshift find the highest-value applicable work.
archive
File the finished part of the run state into a dated archive — shipped items, research, opportunities, the rotated journal, and handled snags. The live files stay lean; the facts stay on disk.
doctor
Read-only Nightshift diagnosis — workspace, rules, markers, session, process lease, watchman, deadline, and classified next actions. Use when a shift looks wrong, recovery is unclear, or the owner asks what Nightshift sees. Never repairs by being invoked.
import-issues
Stage explicitly selected GitHub issues onto the drafting table as quoted source. Never searches, never writes back to GitHub, never installs gh.
purge
Permanently delete this project's Nightshift state. Does not uninstall the plugin.
stop
Issue a stop-work order — pause the shift immediately, leaving unfinished items open.