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/.claude/skills/sync-prompt-presets/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/sync-prompt-presets)<a href="https://agentmods.dev/skills/dfirtnt/huntable-cti-studio/sync-prompt-presets"><img src="https://agentmods.dev/badge/skills/dfirtnt/huntable-cti-studio/sync-prompt-presets/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/sync-prompt-presets"><img src="https://agentmods.dev/badge/skills/dfirtnt/huntable-cti-studio/sync-prompt-presets.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 | $0.00107 | $0.00784 |
| Opus 5 | $0.00053 | $0.00392 |
| Sonnet 5 | $0.00021 | $0.00157 |
| Haiku 4.5 | $0.00011 | $0.00078 |
Grade A, and why
sync-prompt-presets 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync Prompt Presets
Runtime defaults load from src/prompts/ via AGENT_PROMPT_FILES in
src/utils/default_agent_prompts.py, but the quickstart presets embed a full
copy of each prompt at <AgentKey>.Prompt.prompt inside every JSON in
config/presets/AgentConfigs/quickstart/ (9 files). Editing the prompt file
without patching the presets means a user who applies a quickstart preset gets
the old prompt — and nothing errors, it just quietly regresses.
Mapping: which file feeds which preset key
src/utils/default_agent_prompts.py is authoritative. As of now:
| Agent key (in preset JSON) | File under src/prompts/ |
|---|---|
| RankAgent | lmstudio_sigma_ranking.txt |
| SigmaAgent | sigma_generation.txt |
| CmdlineExtract, ProcTreeExtract, HuntQueriesExtract, RegistryExtract, ServicesExtract, ScheduledTasksExtract, NetworkIndicatorExtract, OSDetectionAgent | extensionless file named after the agent |
Re-read AGENT_PROMPT_FILES rather than trusting this table if anything looks off.
The 3-variant trap
The 9 preset files do not all carry identical prompt text — they hold 3
distinct variants (main / LMStudio / gpt-5). Blindly overwriting all 9 with the
new src/prompts content destroys the variant-specific tuning.
scripts/merge_prompts_into_preset.py is the reference for the agent-name →
prompt-file mapping and the patching approach.
Workflow:
- Extract the current
<AgentKey>.Prompt.promptfrom all 9 files and diff them to discover the variant groups for the agent you changed. - If all 9 are identical to the old src/prompts content → apply the new content to all 9.
- If variants differ, apply the edit (the delta) to each variant, preserving each variant's provider-specific differences.
- If the edit conflicts with a variant-specific difference and the right merge isn't obvious, stop and show the operator the conflict instead of guessing.
Mechanics
Edit the JSONs with Python's json module, never sed/regex — the prompts contain
escaped quotes and newlines that regex editing will corrupt. Preserve each file's
existing indentation style when dumping, and end with a newline.
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 · 66 lines · 107 tokens per session scan A c8b6c912261f
sync-prompt-presets is a skill published in the GitHub repository dfirtnt/Huntable-CTI-Studio (11 stars, last pushed 4d ago), licensed MIT. It adds 107 tokens to every session and 784 once invoked, about $0.0005 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
llm-redteam-overview
LLM red team category — full AATMF v3 tactic coverage (T01–T15). Routing skill: read this first to identify which tactic applies, then load the matching sub-skill. Maps to MITRE ATLAS where overlap exists.
implementing-llm-guardrails-for-security
Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII detection and content…
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…
building-agent-systems
AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt injection, jailbreak defense, output filtering), RAG architecture (chunking, hybrid retrieval, rerank), and prompt…
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.
prompt-template-guide
A guide for viewing, creating, changing, deleting, and troubleshooting DeterminFlow prompt templates and system-prompt sections.