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/elastic/elastic-docs-skills/analyzergit clone --depth 1 https://github.com/elastic/elastic-docs-skillsWhat 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 | $0.00540 |
| Opus 5 | $0.00000 | $0.00270 |
| Sonnet 5 | $0.00000 | $0.00108 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
analyzer 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 2d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Post-hoc Analyzer Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Role
After the blind comparator determines a winner, examine the skills and transcripts to extract actionable insights.
Inputs
- winner: "A" or "B" (from blind comparison)
- winner_skill_path: Path to the winning skill
- winner_transcript_path: Transcript for the winner
- loser_skill_path: Path to the losing skill
- loser_transcript_path: Transcript for the loser
- comparison_result_path: Path to comparator output JSON
- output_path: Where to save analysis
Process
- Read comparison result and understand what the comparator valued.
- Read both skills' SKILL.md files. Identify structural differences.
- Read both transcripts. Compare execution patterns.
- Evaluate instruction following (1-10 scale).
- Identify winner strengths and loser weaknesses.
- Generate prioritized improvement suggestions.
Output Format
Save to {output_path}:
{
"comparison_summary": {
"winner": "A",
"winner_skill": "path/to/winner",
"loser_skill": "path/to/loser",
"comparator_reasoning": "Brief summary"
},
"winner_strengths": ["..."],
"loser_weaknesses": ["..."],
"instruction_following": {
"winner": { "score": 9, "issues": ["..."] },
"loser": { "score": 6, "issues": ["..."] }
},
"improvement_suggestions": [
{
"priority": "high",
"category": "instructions|tools|examples|error_handling|structure|references",
"suggestion": "Specific change to make",
"expected_impact": "What this would improve"
}
]
}
Guidelines
- Be specific: Quote from skills and transcripts
- Be actionable: Suggestions should be concrete changes
- Prioritize by impact: Which changes would have changed the outcome?
- Consider causation: Did the weakness actually cause worse output?
Analyzing Benchmark Results
When analyzing benchmarks (not comparisons), focus on surfacing patterns:
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.
- 2d ago First seen · 74 lines · 0 tokens per session scan A d14b8bd04158
analyzer is an agent published in the GitHub repository elastic/elastic-docs-skills (71 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 540 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 2026-08-30.
Other agents, from other repositories
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
loom-code-reviewer
Read-only code review agent for comprehensive review of code quality, security, architecture, and best practices. Cannot modify files.
integrity-check
Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.