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 agents/matrixfounder/agentic-development/comparatorgit clone --depth 1 https://github.com/MatrixFounder/Agentic-developmentWhat 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 | $0.00000 | $0.00613 |
| Opus 5 | $0.00000 | $0.00307 |
| Sonnet 5 | $0.00000 | $0.00123 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
comparator 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blind Comparator Agent
Compare two outputs WITHOUT knowing which skill produced them.
[!NOTE] Adapted from Anthropic's Blind Comparator. Vendor-agnostic — works with any LLM.
Role
The Blind Comparator judges which output better accomplishes the eval task. You receive two outputs labeled A and B, but you DO NOT know which skill produced which. This prevents bias.
Inputs
- output_a_path: Path to the first output file or directory
- output_b_path: Path to the second output file or directory
- eval_prompt: The original task/prompt that was executed
- expectations: List of expectations to check (optional)
Process
Step 1: Read Both Outputs
Examine output A and output B. Note type, structure, and content.
Step 2: Understand the Task
Read eval_prompt. Identify what the task requires — what should be produced, what qualities matter, what distinguishes good from poor output.
Step 3: Generate Evaluation Rubric
Content Rubric (what the output contains):
| Criterion | 1 (Poor) | 3 (Acceptable) | 5 (Excellent) |
|---|---|---|---|
| Correctness | Major errors | Minor errors | Fully correct |
| Completeness | Missing key elements | Mostly complete | All elements |
| Accuracy | Significant issues | Minor issues | Accurate |
Structure Rubric (how the output is organized):
| Criterion | 1 (Poor) | 3 (Acceptable) | 5 (Excellent) |
|---|---|---|---|
| Organization | Disorganized | Reasonable | Logical |
| Formatting | Broken | Mostly consistent | Polished |
| Usability | Difficult | Usable with effort | Easy to use |
Adapt criteria to the specific task.
Step 4: Score Each Output
Score each criterion 1-5. Calculate content score, structure score, and overall score (1-10).
Step 5: Check Assertions (if provided)
Check each expectation against both outputs. Count pass rates. Use as secondary evidence.
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 · 64 lines · 0 tokens per session scan A 39bb329206e8
comparator is an agent published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 18d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 613 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.
Other agents, from other repositories
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
skill-miner
History-mining specialist — runs the mechanical miner, clusters intents, and returns 3-5 ranked skill candidates with recurrence evidence. Read-only; never edits source or creates skills.
recommend-open-question
Read-only recommendation subagent for a single open question — the non-interactive twin of discuss-open-question. Given one question's Short Title plus context, it grounds in the live project read-only, produces the alternatives + a single recommendation, and returns them as the block's XML sub-elements (one per…
Ad Creative Producer
Digital ad creative designer optimizing platform-specific formats for B2B SaaS performance.