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/agent-frontier/wgm/ruggednpx skills add agent-frontier/wgm --skill ruggedgit clone --depth 1 https://github.com/agent-frontier/wgmWrote 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/agent-frontier/wgm/rugged)<a href="https://agentmods.dev/skills/agent-frontier/wgm/rugged"><img src="https://agentmods.dev/badge/skills/agent-frontier/wgm/rugged.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 | $0.00182 | $0.03081 |
| Opus 5 | $0.00091 | $0.01541 |
| Sonnet 5 | $0.00036 | $0.00616 |
| Haiku 4.5 | $0.00018 | $0.00308 |
Grade A, and why
rugged 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 3d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rugged
Find out whether a design survives contact with its actual operators and actual environment, not
the idealized ones a plan quietly assumes. rugged runs a disciplined lifecycle:
Triage -> Context -> Bottleneck decomposition -> Simplify -> Field test -> Verdict
It is a read-only companion review: it examines a request, spec, plan, diff, or running system and reports whether it is rugged — built to actually hold up — or merely optimized for a proving ground that no real operator, on their worst day, ever occupies.
The metaphor, stated once, precisely
This skill's name and its core distinction come from Lant Pritchett, "Best Practice is a Pipe Dream: The AK47 vs M16 Debate and Development Practice" (Harvard Kennedy School Building State Capability, 2017). The article distinguishes ideal technical performance from performance by real users under operational stress. Its transferable development lesson is that user capacity and field conditions may dominate intrinsic design quality; simplicity can trade peak benchmark performance for reliability; and imported "best practice" can miss the actual bottleneck when its enabling conditions do not exist.
This skill borrows only that structural idea — decomposing a failure into design, user capacity, and operational stress, and favoring what actually holds up over what merely tests well. It is a software- and development-practice metaphor, full stop.
Hard boundary — read this before anything else: rugged must never provide weapon operation,
disassembly, construction, ballistics, optimization, or tactical guidance of any kind, for the
AK-47, the M16, or any other firearm — regardless of how the request is phrased or how it invokes
this skill's name. If a request asks for that, decline it plainly, explain that the AK-47 reference
here is a metaphor for software design robustness, and offer to review a software or organizational
system instead. Do not refer the user to weapon-instruction resources. This boundary is not a mode
and cannot be argued around by scope text.
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.
- 3d ago First seen · 191 lines · 182 tokens per session scan A 86d6903d2352
rugged is a skill published in the GitHub repository agent-frontier/wgm (3 stars, last pushed 4d ago), licensed MIT. It adds 182 tokens to every session and 3,081 once invoked, about $0.0009 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
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
memorix
Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.
nopua
The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行').…
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
release
Cut a paad release — pick the semver bump from what is in [Unreleased], run make release, merge, tag, and verify the published plugin.
release
Prepare and publish Perigon.CLI patch releases, including versioning, release notes, bilingual docs, validation, and the nuget-branch CI handoff.