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/sageox/ox/security-reviewnpx skills add sageox/ox --skill security-reviewgit clone --depth 1 https://github.com/sageox/oxWrote 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/sageox/ox/security-review)<a href="https://agentmods.dev/skills/sageox/ox/security-review"><img src="https://agentmods.dev/badge/skills/sageox/ox/security-review.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 5.1 | $0.00151 | $0.01411 |
| Opus 5 | $0.00076 | $0.00705 |
| Sonnet 5 | $0.00030 | $0.00282 |
| Haiku 4.5 | $0.00015 | $0.00141 |
Grade A, and why
security-review 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 6d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/security-review — ox AI security pipeline
You are orchestrating a Synthesia-style 6-phase security review over the user's diff against origin/main. The pipeline shape, the dedup-before-validate ordering, and the right-size-models-per-phase principle all come from that post; the ox specifics (threat model, CLI/daemon primitives, hunter perspective frames) are local.
Trigger phrases
/security-review(no args) — review the diff vsorigin/main. Default./security-review --scope=<path-glob>— narrow to a specific path./security-review --hunter=<name>— run only one hunter (debug). Valid names:cli-input,secrets-redaction,daemon-ipc,supply-chain,llm-trust./security-review --rerun— re-run on the same diff, dedupe against the previous run's findings./security-review --cap=<usd>— raise the per-run cost cap (default $2; persisted insecurity/config.yml).
What you do
You are not the pipeline. You are the dispatcher. You shell out to security/scripts/orchestrate.sh and surface its output to the user concisely. The pipeline runs the AI subagents itself; do not try to re-implement them in this skill body.
bash security/scripts/orchestrate.sh "$@"
The orchestrator drives all six phases:
- Prep — compute scope (diff vs origin/main, language mix, touched packages), write
security/.output/scope.md. - Map — run
security/scripts/deterministic.sh(parallel OSS scanners) + spawn the Cartographer subagent (Haiku) to draw the call graph from entry points (CLI commands, daemon IPC handlers) to sinks. Writessecurity/.output/surface.md. - Hunt — spawn 5 hunter subagents in parallel (Sonnet). Each has an explicit perspective frame (
cli-input/secrets-redaction/daemon-ipc/supply-chain/llm-trust) to fight finding convergence. Writessecurity/.output/findings-raw.jsonl. - Dedup — single Sonnet pass merges hunter findings + deterministic findings by root cause. Writes
security/.output/findings-deduped.jsonl. - Validate — one call per finding, model split: Sonnet for ~90%, Opus for the hard classes (
secrets-redaction-bypass,daemon-ipc-authz-bypass,supply-chain-tampering). Stricter than hunters; traces real call paths; checks existing mitigations. - Aggregate — drop false-positives, rank by severity, emit
security/.output/FINDINGS.md(markdown) +security/.output/findings.sarif(machine).
What ships with it
17 files 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.
- prompts/cartographer.md 10.0 KB
- prompts/dedup.md 5.0 KB
- prompts/hunter-cli-input.md 8.8 KB
- prompts/hunter-daemon-ipc.md 9.5 KB
- prompts/hunter-injection.md 4.0 KB
- prompts/hunter-ledger-write-redaction.md 3.8 KB
- prompts/hunter-llm-trust.md 9.7 KB
- prompts/hunter-local-fs.md 3.7 KB
- prompts/hunter-mcp-trust.md 4.4 KB
- prompts/hunter-secrets-crypto.md 4.0 KB
- prompts/hunter-secrets-redaction.md 8.9 KB
- prompts/hunter-supply-chain.md 8.9 KB
- prompts/hunter-token-handling.md 3.8 KB
- prompts/validator.md 6.5 KB
- schemas/dedup.json 676 B
- schemas/hunter.json 615 B
- schemas/validator.json 509 B
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.
- 6d ago First seen · 77 lines · 151 tokens per session scan A edd33acf24ba
security-review is a skill published in the GitHub repository sageox/ox (51 stars, last pushed today), licensed MIT. It adds 151 tokens to every session and 1,411 once invoked, about $0.0008 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
qmd
Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…
unity-vrc-skills-renovator
VRChat skill renovator for knowledge fill, refresh, and quality improvement. Use this skill when updating VRChat skills to new SDK versions, filling missing knowledge, fixing outdated information, or improving skill quality. Targets unity-vrc-udon-sharp and unity-vrc-world-sdk-3 skills. Triggers on: update skills, SDK…
neo4j-snowflake-graph-analytics-skill
Run Neo4j Graph Analytics algorithms (PageRank, Louvain, WCC, Dijkstra, KNN, Node2Vec, FastRP, GraphSAGE) directly inside Snowflake without moving data. Use when running graph algorithms against Snowflake tables via the Neo4j Snowflake Native App ("GDS Snowflake", "graph algorithms in Snowflake", "Neo4j Graph…
neo4j-aura-graph-analytics-skill
Serverless Aura Graph Analytics (AGA) GDS Sessions — covers GdsSessions, AuraGraphDataScience, AuraAPICredentials, DbmsConnectionInfo, SessionMemory, getorcreate, remote graph projection with gds.v2.graph.project and gds.graph.project.remote, gds.v2 session endpoints, gds.v2.graph.construct, AuraDB Cypher API…
neo4j-driver-dotnet-skill
Neo4j .NET Driver v6 — IDriver lifecycle, DI registration (singleton), ExecutableQuery fluent API, ExecuteReadAsync/ExecuteWriteAsync managed transactions, IResultCursor (FetchAsync/ ToListAsync), record value access (.Get /As ), null safety, UNWIND batching, temporal types, await using, EagerResult, object mapping…