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 skills add suiflex/ForgeGuard --skill engineeringgit clone --depth 1 https://github.com/suiflex/ForgeGuardWrote 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/suiflex/forgeguard/engineering)<a href="https://agentmods.dev/skills/suiflex/forgeguard/engineering"><img src="https://agentmods.dev/badge/skills/suiflex/forgeguard/engineering/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/suiflex/forgeguard/engineering"><img src="https://agentmods.dev/badge/skills/suiflex/forgeguard/engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.01444 |
| Opus 5.5 | $0.00022 | $0.00578 |
| Sonnet 5.5 | $0.00011 | $0.00289 |
| Haiku 4.5 | $0.00006 | $0.00144 |
Grade A, and why
forgeguard-engineering 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 1mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ForgeGuard Engineering
Follow: inspect → design → implement → test → review → verify.
For non-code work, interpret the workflow as inspect → frame → produce → check → review → verify. Do not invent code-shaped steps for a product brief, investigation, test session, analysis, decision, or operational task.
Work surgically
- Inspect the affected code, tests, contracts, schemas, direct callers, and compatibility surface before editing.
- Inspect through the code graph before reading files:
forgeguard memory symbol <name>returns the signature, callers, callees, dependents, and related tests;--detail snippetadds only that symbol's source;forgeguard memory impactmaps the current diff to affected symbols, tests, and risk. Read a whole file when the graph cannot answer, not first. - Resolve missing facts with read-only inspection. When unresolved ambiguity materially changes behavior, data, security, scope, cost, or external or irreversible state, use the host's native structured user-input tool and wait; otherwise state the safest reversible assumption.
- Reuse an existing project pattern only when its purpose and change reasons match. Prefer the standard library and installed dependencies over new abstractions or packages.
- Make every changed line trace to the objective. Do not refactor adjacent code or remove pre-existing dead code; remove only orphans created by the change.
- Choose the smallest safe design. Define only the relevant bounds, failures, complexity, I/O, and concurrency risks.
Reject AI slop
- Do not add generic boilerplate, speculative abstractions, duplicate helpers, decorative comments, or dependencies without a requirement demonstrated in the repository.
- Do not invent requirements, APIs, schemas, files, command results, metrics, or evidence. Inspect them directly; label anything still unknown as unverified.
- Do not disguise incomplete work with placeholders, fake data, silent fallbacks, swallowed errors, or TODO-only implementations unless the user explicitly requested a stub or test fixture.
- Deliver the smallest complete path through the real code, remove only additions made obsolete by the change, and prove changed behavior with the narrowest executable check.
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.
- agents/openai.yaml 184 B
- references/ai.md 918 B
- references/algorithms.md 1.0 KB
- references/backend.md 613 B
- references/database.md 694 B
- references/deep-learning.md 807 B
- references/frontend.md 804 B
- references/general-work.md 2.2 KB
- references/ml.md 820 B
- references/mlops.md 767 B
- references/mobile.md 861 B
- references/testing.md 631 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.
- 1mo ago Changed · +1 lines 841c446787fd
- 1mo ago First seen · 82 lines · 55 tokens per session scan A fac16ba599b5
forgeguard-engineering is a skill published in the GitHub repository suiflex/ForgeGuard (14 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 1,444 once invoked, about $0.0002 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…