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/gyuha/forge/fg-securitynpx skills add gyuha/forge --skill fg-securitygit clone --depth 1 https://github.com/gyuha/forgeWrote 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/gyuha/forge/fg-security)<a href="https://agentmods.dev/skills/gyuha/forge/fg-security"><img src="https://agentmods.dev/badge/skills/gyuha/forge/fg-security.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 | $0.00126 | $0.02842 |
| Opus 5 | $0.00063 | $0.01421 |
| Sonnet 5 | $0.00025 | $0.00568 |
| Haiku 4.5 | $0.00013 | $0.00284 |
Grade A, and why
fg-security 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 today.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
12 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.
- AI-AND-LLM.md 11 KB
- ATTACK-CLASSES.md 14 KB
- AUDIT.md 11 KB
- CLIENT-SIDE.md 8.5 KB
- HUNTING.md 6.4 KB
- LICENSE 1.1 KB
- MEMORY-SAFETY-AND-BINARY.md 8.1 KB
- RECONNAISSANCE.md 3.3 KB
- report-schema.json 8.1 KB
- validate-findings.cjs 6.6 KB runs code
- VALIDATION-AND-REPORTING.md 8.2 KB
- WEB-PROTOCOL-AND-AUTH.md 14 KB
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.
- today Changed · +2 lines 565e67ebe549
- 3d ago First seen · 97 lines · 126 tokens per session scan A dd6269d7be20
fg-security is a skill published in the GitHub repository gyuha/forge (4 stars, last pushed today), with no licence file. It adds 126 tokens to every session and 2,842 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
work
Pick up ready leaf yaks and implement them — dispatch subagents in isolated worktrees, then merge back to main.
yak-worktree-workflow
Use when starting work on a yak - sets up an isolated git worktree, reads yak context, and guides the full cycle from claiming through merge and cleanup.
issue-comment
Handle a non-build maintainer comment on an issue or PR — close, reopen, label, dedupe, answer a brief question, or triage. Action-only; redirect anything that needs code changes to /build.
chat
Conversational assistant for messaging-platform threads (Slack, Discord). Answer questions about repos, PRs, and issues, explain code, and guide users to the natural-language workflow triggers listed in the system prompt.
file-todos
Manage file-based todos in todos/ directory. Use when creating, triaging, or tracking todos and integrating them with code review.
lavra-work
Execute work on one or many beads -- auto-routes between single-bead, sequential, and multi-bead parallel paths based on input.