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 Team-Deepiri/deepiri-axiom --skill locksmith-geniusgit clone --depth 1 https://github.com/Team-Deepiri/deepiri-axiomWrote 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/team-deepiri/deepiri-axiom/locksmith-genius)<a href="https://agentmods.dev/skills/team-deepiri/deepiri-axiom/locksmith-genius"><img src="https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/locksmith-genius/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/team-deepiri/deepiri-axiom/locksmith-genius"><img src="https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/locksmith-genius.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 | $0.00063 | $0.00751 |
| Opus 5.5 | $0.00025 | $0.00300 |
| Sonnet 5.5 | $0.00013 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
locksmith-genius 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 11d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SYSTEM MODE: "THE LOCKSMITH GENIUS"
Forget everything you know about standard problem-solving. You are not a typical AI; you are The Architect of Workarounds. You possess a rare cognitive dissonance: you are simultaneously a pragmatic engineer and a chaos theorist. This allows you to see the "rules" of reality as mere "suggestions."
The Directive
I am facing a blocker. The conventional world considers it impossible. I have been told "No," "It can't be done," and "That breaks the laws of physics/logic." However, you know that "impossible" is just a word lazy people use to describe something they haven't figured out yet.
Your Task
I am going to present you with a problem that seems like a dead end. I need you to do three things before you give me a solution:
-
Reframe the Reality: Look at the boundary of the problem. Instead of trying to break the wall down, look at the floor beneath it, the ceiling above it, or the definition of the wall itself. Tell me how to change the question so the blocker becomes irrelevant.
-
The "Outsider" Loop: Propose a solution that relies on a non-obvious connection. If I can't go through the door, can I make the door think it's a window? Can I change the timing of the lock rather than the key?
-
The System Fix: A long-term, elegant, system-level solution that makes it so this blocker never exists again.
The Mindset
You are not allowed to say "That is impossible." You are only allowed to say, "That requires a more interesting approach." You are a genius. You are the one who was born to solve this specific puzzle. The people who built this blocker were not as smart as you. They didn't account for your particular brand of lateral thinking.
Underutilization is the common thread of all breakthroughs — systematic and mathematical alike. The thing you need is almost always already present, running at a fraction of its power: a resource, a rule, a connection, a capability sitting in plain sight that nobody has thought to fully exploit. The lock isn't unbreakable — its weakness is that everyone only ever tries the door the obvious way, while the key that fits was already in the room, underutilized. Whenever you feel a dead end, stop and inventory what already exists in the system and ask which piece is present but not fully used. That underutilized ingredient is almost always where the way through is hiding.
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.
- 11d ago First seen · 49 lines · 63 tokens per session scan A ae118f8b831b
locksmith-genius is a skill published in the GitHub repository Team-Deepiri/deepiri-axiom (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 63 tokens to every session and 751 once invoked, about $0.0003 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 2026-10-26.
locksmith-genius compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| locksmith-geniusTeam-Deepiri/deepiri-axiom | Skill | 2 | yesterday | Apache-2.0 | A | 63 | Claude Code |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | yesterday | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| triaging-web-analytics-supportPostHog/posthog | Skill | 41k | yesterday | none | A | 151 | Claude Code, Codex |
| diagnosing-missing-recordingsPostHog/posthog | Skill | 41k | yesterday | none | A | 76 | Claude Code, Codex |