Borrowing it
Nothing to install: this file belongs to dfirtnt/Huntable-CTI-Studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dfirtnt/Huntable-CTI-Studio/main/.agents/skills/huntable-eval-retrieval/SKILL.mdgit clone --depth 1 https://github.com/dfirtnt/Huntable-CTI-StudioWrote 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/dfirtnt/huntable-cti-studio/huntable-eval-retrieval)<a href="https://agentmods.dev/skills/dfirtnt/huntable-cti-studio/huntable-eval-retrieval"><img src="https://agentmods.dev/badge/skills/dfirtnt/huntable-cti-studio/huntable-eval-retrieval/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/skills/dfirtnt/huntable-cti-studio/huntable-eval-retrieval"><img src="https://agentmods.dev/badge/skills/dfirtnt/huntable-cti-studio/huntable-eval-retrieval.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 | $0.00089 | $0.00669 |
| Opus 5 | $0.00044 | $0.00334 |
| Sonnet 5 | $0.00018 | $0.00134 |
| Haiku 4.5 | $0.00009 | $0.00067 |
Grade A, and why
huntable-eval-retrieval 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 12d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huntable eval retrieval
Use the MCP eval tools to retrieve read-only evaluation evidence. Prefer the convenience tool so callers do not need to remember low-level parameters.
Default workflow
- Call
get_eval_runwith the run selector, for examplev5139a. - If comparing replicates, call it again for
v5139band comparerun_index, article IDs, and execution IDs. - For one article, call
get_eval_runwith both the run selector andarticle_id. - For a trace, take the returned
execution_idand callget_workflow_execution_traceseparately. - Report schema versions, selected records, skipped/capped records, and any MCP size-limit errors clearly.
Tool selection
get_eval_run: normal entry point. Accepts a run label such asv5139aand optionalarticle_idorsubagent.get_eval_bundles_by_config: use when the caller explicitly needs a larger config-wide export or needs control over the bundle cap.get_article_eval_bundle: use for direct article bundle retrieval when the caller needs explicitslim, Langfuse, or trace settings.get_workflow_execution_trace: use for the workflow trace. Keepinclude_eval_bundles=falseunless the caller explicitly requests embedded bundles and the response is known to fit the MCP limit.get_eval_bundle: use when an exact execution ID and agent name are already known.
Run labels
v5139selects all completed runs under numeric config version 5139.v5139aselects the first chronological completed replicate per article and subagent (run_index=0).v5139bselects the second (run_index=1).
Do not infer equivalence from the numeric version alone when a lettered run selector is provided. Compare execution IDs to prove whether runs differ.
Safety and output limits
All retrieval tools are read-only. Do not call diagnosis or write tools unless the user separately requests that action. Keep bundles slim by default and retrieve traces separately; a combined article bundle plus trace can exceed the MCP client's 1 MB result limit.
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.
- 12d ago First seen · 63 lines · 89 tokens per session scan A bbfcb5d1f3da
huntable-eval-retrieval is a skill published in the GitHub repository dfirtnt/Huntable-CTI-Studio (11 stars, last pushed 4d ago), licensed MIT. It adds 89 tokens to every session and 669 once invoked, about $0.0004 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
AI & LLM Security
LLM and AI application security testing — prompt injection, jailbreak resistance, OWASP LLM Top 10 (2025), RAG and agent/tool-use security, model supply chain, and AI red teaming for authorized assessments.
configuring-windows-event-logging-for-detection
Configures Windows Event Logging with advanced audit policies to generate high-fidelity security events for threat detection and forensic investigation. Use when enabling audit policies for logon events, process creation, privilege use, and object access to feed SIEM detection rules. Activates for requests involving…
ai-llm-security-review
Use for AI/LLM security assessments, prompt injection, RAG security, agent/tool permissioning, model supply chain, LLM red teaming, AI governance, eval design, data leakage, jailbreak testing, and secure AI application review.
operate-ai-stack
Develop, test, and troubleshoot this generated AI or ML workload across its framework, model and embedding providers, retrieval stores, interfaces, training, serving, and observability layers. Use when changing prompts, tools, agents, RAG, MCP, inference, fine-tuning, evaluations, or provider integration.
project-workflow
Develop, test, and maintain this generated Python project using its recorded Copier choices and uv toolchain. Use for any code, dependency, configuration, documentation, or test change in this project, including simple libraries, CLIs, APIs, and layered AI or ML applications.
sast-dast-coordinator
../../../appsec-devsecops/sast-dast-coordinator/SKILL.md.