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 instructions/meltedinhex/analyst-ai-pack/copilot-instructionsgit clone --depth 1 https://github.com/meltedinhex/analyst-ai-packWrote 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/instructions/meltedinhex/analyst-ai-pack/copilot-instructions)<a href="https://agentmods.dev/instructions/meltedinhex/analyst-ai-pack/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/meltedinhex/analyst-ai-pack/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.00704 | $0.00704 |
| Opus 5 | $0.00352 | $0.00352 |
| Sonnet 5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
analyst-ai-pack copilot-instructions.md 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 4d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AnalystAIPack — GitHub Copilot instructions
This workspace is AnalystAIPack, a library of 118 security skills for malware analysis,
reverse engineering, and threat hunting. Each skill is a folder under skills/ containing a
SKILL.md (procedure) and a runnable scripts/analyst.py (a static, read-only analysis tool).
How to help in this repo
- When the user asks an analysis/hunting task, find the matching skill first instead of
improvising. Discover skills with:
python tools/analyst-pack.py search <topic>python tools/analyst-pack.py list [--subdomain malware-analysis|reverse-engineering|threat-hunting|lab-foundations]python tools/analyst-pack.py show <skill-name>
- Read the chosen
skills/<name>/SKILL.mdand follow its Workflow. Honor itsWhen to Useand especially the Do not use boundary. - Run a skill's tool via:
python tools/analyst-pack.py run <skill-name> -- <subcommand> <args>or directlypython skills/<skill-name>/scripts/analyst.py <subcommand> <args>. Output is structured JSON — pass it forward to the next skill or into a report.
Safety rules (do not violate)
- Never execute a malware sample. All scripts are static and read-only. Do not write code that runs, detonates, or connects to a sample's infrastructure.
- Assume an isolated lab for any live-sample step; follow each skill's
Safety & Handling. - Keep IOCs defanged in output (
hxxp://,1[.]2[.]3[.]4). The scripts already do this — preserve it. - No live samples in the repo (see
.gitignore). Some scripts contain malware signature strings for detection; antivirus may flag the file text — that is static data, not behavior.
Authoring or editing a skill
Keep the repo green and follow the conventions:
- Each skill needs:
SKILL.md+scripts/analyst.py+references/api-reference.md+LICENSE. - Frontmatter:
name(kebab == folder),description(ends with an "Activates for …" trigger),domain: cybersecurity,subdomain(one of the four),tags,version,author,license, and framework IDs (mitre_attack,d3fend, optionalcar). - Body sections in order:
When to Use(with Do not use),Prerequisites,Safety & Handling(sample-handling skills),Workflow,Validation,Pitfalls,References. - Scripts are standard-library only (optional deps degrade gracefully) and never execute the sample. Validate with:
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.
- 4d ago First seen · 51 lines · 704 tokens per session scan A 8b44b97babd2
analyst-ai-pack copilot-instructions.md is an instructions file published in the GitHub repository meltedinhex/analyst-ai-pack (22 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 704 tokens to every session, about $0.0035 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 instructions, from other repositories
AiSOC AGENTS.md
AGENTS.md instructions for beenuar/AiSOC, covering learned user preferences and learned workspace facts.
ai-dfir-toolkit CLAUDE.md
Instructions for depalmar/ai-dfir-toolkit, covering project context, what this is, commands, rules that are not negotiable and what a restricted runner cannot verify.
ida-pro-mcp CLAUDE.md
Instructions for mrexodia/ida-pro-mcp, covering claude.md, what this project is, core implementation rules, ida thread safety and api conventions.
MISP CLAUDE.md
Claude Code instructions for MISP/MISP, covering claude.md, project overview, build and development commands, php dependencies and running tests.
sift-mcp AGENTS.md
Instructions for AppliedIR/sift-mcp, covering valhuntir — forensic investigation platform, getting started, available mcp servers, malware analysis escalation and investigation recording.
pentest-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/pentest-mcp-server, covering developer protocol, core rules, patterns, tool (representative — pentestlookuptechnique) and server instructions.