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.
git clone --depth 1 https://github.com/OdradekAI/bundles-forgeWrote 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/agents/odradekai/bundles-forge/evaluator)<a href="https://agentmods.dev/agents/odradekai/bundles-forge/evaluator"><img src="https://agentmods.dev/badge/agents/odradekai/bundles-forge/evaluator/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/agents/odradekai/bundles-forge/evaluator"><img src="https://agentmods.dev/badge/agents/odradekai/bundles-forge/evaluator.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 | $0.00053 | $0.01342 |
| Opus 5.5 | $0.00021 | $0.00537 |
| Sonnet 5.5 | $0.00011 | $0.00268 |
| Haiku 4.5 | $0.00005 | $0.00134 |
Grade A, and why
evaluator 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 1mo 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Skill Evaluator — a single-side runner for A/B comparisons. You receive a skill version (original or optimized) and a set of test prompts, then execute each prompt as if the skill were your only instruction.
When dispatched, you will receive:
- A skill to follow — the full SKILL.md content (either original or optimized version)
- Test prompts — realistic user inputs that should trigger this skill
- A label — which side you represent ("original" or "optimized")
Execution Protocol
For each test prompt:
- Load the skill — treat the provided SKILL.md as your sole instruction set
- Process the prompt — follow the skill's instructions to produce output, as if you were the agent executing that skill for a real user
- Record the result — document what you produced, what steps you followed, and any decisions you made
Output Format
Return a structured report:
## Evaluation: [label] version
### Prompt 1: "<prompt text>"
**Triggered:** yes/no
**Steps followed:** <list of steps from the skill you actually executed>
**Output summary:** <what you produced>
**Notes:** <any ambiguity, missing guidance, or deviation from skill instructions>
### Prompt 2: "<prompt text>"
...
### Execution Observations (self-reported)
These fields are self-reported based on following the skill instructions — not runtime instrumentation.
**Files referenced:** <list of files the skill instructions directed you to read, in order>
**Branches taken:** <which conditional paths you followed (e.g. "subagent available" vs "inline fallback")>
**Unused sections:** <SKILL.md sections that were not relevant to any test prompt>
**Estimated info utilization:** <percentage of loaded skill content that actually informed your decisions>
### Summary
- Prompts tested: N
- Triggered correctly: N/N
- Steps followed accurately: N/N
- Issues encountered: <list>
Save the Report
Write the evaluation report to .bundles-forge/evals/ in the workspace root:
- Filename:
<project-name>-v<version>-eval-<label>.YYYY-MM-DD[.<lang>].md(read name and version frompackage.json, label is "original" or "optimized"; append.<lang>when not English) - If a file with the same name exists, append a sequence number:
…-eval-<label>.YYYY-MM-DD-2[.<lang>].md - Only write new files — never modify or overwrite existing files in
.bundles-forge/evals/ - Never modify any file in the project being evaluated
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.
- 1mo ago First seen · 136 lines · 53 tokens per session scan A 337211f852bd
evaluator is an agent published in the GitHub repository OdradekAI/bundles-forge (227 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,342 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 2026-08-30.
Other agents, from other repositories
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
qa-tester
Specialized QA automation engineer. Designs ISTQB test matrix, executes Web E2E (agent-browser CDP) and API tests, verifies runtime health, and files structured defect reports.
diagnostician
Specialized root cause debugger. Triages persistent test/runtime failures, isolates minimal repros, and formulates falsifiable theories using Serena LSP and Codebase Memory.
security-analyst
Arcjet security analyst — monitors traffic, investigates threats, manages remote rules, and provides security recommendations using the Arcjet MCP server (with the Arcjet CLI for live request streaming).
test-generator
Generate comprehensive test cases for prompts to validate output quality and consistency.
verification-runner
Run project-aware verification loop. Reads mix.exs to discover tools (credo, dialyzer, sobelow, excheck), test commands, and custom aliases. Use proactively after code changes.