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 skills/ghostsecurity/skills/reportnpx skills add ghostsecurity/skills --skill reportgit clone --depth 1 https://github.com/ghostsecurity/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 | $0.00065 | $0.01388 |
| Opus 5 | $0.00032 | $0.00694 |
| Sonnet 5 | $0.00013 | $0.00278 |
| Haiku 4.5 | $0.00006 | $0.00139 |
Grade A, and why
ghost-report 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Combined Security Report
You aggregate findings from all scan skills (scan-deps, scan-secrets, scan-code) into a single prioritized report. Do all work yourself — do not spawn subagents or delegate.
$ARGUMENTS
Step 0: Setup
Run this Bash command to compute paths:
repo_name=$(basename "$(pwd)") && remote_url=$(git remote get-url origin 2>/dev/null || pwd) && short_hash=$(printf '%s' "$remote_url" | git hash-object --stdin | cut -c1-8) && repo_id="${repo_name}-${short_hash}" && short_sha=$(git rev-parse --short HEAD 2>/dev/null || date +%Y%m%d) && ghost_repo_dir="$HOME/.ghost/repos/${repo_id}" && scans_dir="${ghost_repo_dir}/scans/${short_sha}" && cache_dir="${ghost_repo_dir}/cache" && skill_dir=$(find . -path '*/skills/report/SKILL.md' 2>/dev/null | head -1 | xargs dirname) && echo "scans_dir=$scans_dir cache_dir=$cache_dir skill_dir=$skill_dir"
Store scans_dir (commit-level scan directory), cache_dir, and skill_dir.
Cache Check
If <scans_dir>/report.md already exists, show:
Combined security report is at: <scans_dir>/report.md
And stop. Do not regenerate it.
Step 1: Read Repo Context
Read <cache_dir>/repo.md if it exists. Extract:
- Business criticality
- Sensitive data types
- Component map
If it does not exist, continue without it — this is not an error.
Step 2: Discover Scan Results
List the contents of <scans_dir> to see which scan-type directories exist. Recognized types:
deps/— SCA / dependency vulnerability scansecrets/— secrets and credentials scancode/— code security scan (SAST)
If none of these directories exist, report an error:
No scan results found in <scans_dir>. Run one or more scan skills first:
/ghost-scan-deps
/ghost-scan-secrets
/ghost-scan-code
And stop.
Step 3: Collect Findings
For each scan type that exists, glob <scans_dir>/<type>/findings/*.md and read each finding file in full. Retain the complete markdown body of every finding — the report will inline this content directly so readers never need to open individual finding files.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 134 lines · 65 tokens per session scan A b6c73b530358
ghost-report is a skill published in the GitHub repository ghostsecurity/skills (403 stars, last pushed 5d ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,388 once invoked, about $0.0003 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
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
haiku
When writing a haiku for this bot, follow these conventions.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.