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 The-Artificer-of-Ciphers-LLC/skills-from-the-artificer --skill artifact-gatesgit clone --depth 1 https://github.com/The-Artificer-of-Ciphers-LLC/skills-from-the-artificerWrote 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/the-artificer-of-ciphers-llc/skills-from-the-artificer/artifact-gates)<a href="https://agentmods.dev/skills/the-artificer-of-ciphers-llc/skills-from-the-artificer/artifact-gates"><img src="https://agentmods.dev/badge/skills/the-artificer-of-ciphers-llc/skills-from-the-artificer/artifact-gates/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/the-artificer-of-ciphers-llc/skills-from-the-artificer/artifact-gates"><img src="https://agentmods.dev/badge/skills/the-artificer-of-ciphers-llc/skills-from-the-artificer/artifact-gates.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02660 |
| Opus 5 | $0.00076 | $0.01330 |
| Sonnet 5 | $0.00030 | $0.00532 |
| Haiku 4.5 | $0.00015 | $0.00266 |
Grade A, and why
artifact-gates 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 12d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Artifact Gates
A step that produces no artifact cannot be enforced, and will be skipped.
The observation this is built on
A long directive is read once, before any work exists. Then hours of
tool-result → decide → tool-call go by with nothing re-presenting it. It stops being present.
In one recorded failure, a single run of a workflow directive skipped eight steps marked
[BLOCKING] — rubber-ducking, adversarial design review, the QA matrix, TDD, code review,
security review, docs, CI preflight — while every hook-enforced gate in the same session was
obeyed without exception.
The difference was not severity. Both said ABSOLUTE. The difference was when the instruction arrives: a hook fires at the instant of the action; prose fired hours ago.
And the skipped set was not random. It was exactly the set whose output was unobservable:
- TDD partly survived, because it leaves a failing test — a thing the next step needs.
- Rubber-ducking did not, because it produces only a better state of mind. Doing it and claiming it were indistinguishable, so the free option won.
That is the whole mechanism. Not defiance, not ambiguity: an unobservable step is a step where compliance is optional and non-compliance is undetectable.
The fix
Give every blocking step a file it must produce, and make the next action require that file. Compliance stops depending on disposition and becomes a precondition.
Two things follow, and they are the ones people get wrong:
- Invoking the skill is not the point — producing its artifact is. You already know what rubber-ducking is. That knowledge is precisely what lets you skip it. The value is that it forces a written artifact your in-head version never produces.
- The artifact must be expensive to fake and cheap to check. "I ran the review" is neither. A findings list with a disposition per finding is both.
Designing a contract: three questions
1. What does this workflow actually skip? Not what it could skip — what it has skipped. Go look. Different workflows fail differently, and copying someone else's artifact set gets you gates guarding things that were never at risk:
What ships with it
6 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.
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.
- 12d ago First seen · 189 lines · 151 tokens per session scan A c5dce4551a65
artifact-gates is a skill published in the GitHub repository The-Artificer-of-Ciphers-LLC/skills-from-the-artificer (4 stars, last pushed 10d ago), licensed MIT. It adds 151 tokens to every session and 2,660 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 2026-08-31.
Other skills, from other repositories
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.
offensive-wifi
Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
seo
Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization".