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 wildcat-finance/skills --skill fiatgit clone --depth 1 https://github.com/wildcat-finance/skillsWrote 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/wildcat-finance/skills/fiat)<a href="https://agentmods.dev/skills/wildcat-finance/skills/fiat"><img src="https://agentmods.dev/badge/skills/wildcat-finance/skills/fiat/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/wildcat-finance/skills/fiat"><img src="https://agentmods.dev/badge/skills/wildcat-finance/skills/fiat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 154 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 627 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 160 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Agent Snooping · line 290 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00078 | $0.17163 |
| Opus 5 | $0.00039 | $0.08582 |
| Sonnet 5 | $0.00016 | $0.03433 |
| Haiku 4.5 | $0.00008 | $0.01716 |
Grade A, and why
fiat 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 4d 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 — 975 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fiat
Where this sits
Fiat owns the delivery controller, not Hexaemeron's bundled audit or prose skills. Its version, held frontier, next job, and maturity state live in EVOLUTION.md. Read that ledger before suggesting, starting, or resuming work intended to advance Fiat itself.
Current frontier. The ledger above is authoritative. Never substitute Hexaemeron's plugin-wide Solidity frontier for Fiat's own held target.
Synkrisis is outside this controller loop. It compares declared runs and stops there: it cannot select work, file an issue, mutate a repository, or dispatch Fiat. A finding remains evidence for a person to route, never a controller directive.
Phase skills
Six sibling skills carry the loop's content contracts; Fiat runs the loop and defers to them rather than restating their rules. Each slots in as follows:
| Skill | Slots into | Carries |
|---|---|---|
| protasis | study and runbook phases | what a study must answer, what a runbook step must contain, when a topic decomposes first |
| phylax | implement phase | the boundaries a step introduces and the control each needs |
| ephoros | implement phase | what the step must emit once it runs unattended |
| metron | implement phase | refusal of any speed-motivated change without a recorded before and after |
| elenchus | implement phase and audit rounds | any failure surfaced mid-step or mid-round, worked to its cause |
| hypomnema | prose phase | what the step records and where it lives, before the masks run |
Their lints run in every audit round, so meeting them during the step is cheaper than meeting them in the round. The phase notes below say how each one is applied.
Let there be light.
Drive the whole loop from durable controller state, never from conversation history. The controller emits one directive at a time; do the work it names, receipt it, ask for the next one. A phase without a receipt did not happen. Every state-backed command first validates the required version-1 container spine in deterministic order. A missing or wrong-kind container stops with one value-free path-and-kind diagnosis before a reader or writer can traverse it.
What ships with it
16 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 495 B
- DEMONSTRATION.md 2.3 KB
- EVOLUTION.md 65 KB
- references/audit-loop.md 14 KB
- references/checkpoint-identity.md 7.3 KB
- references/controller-checkpoint.md 11 KB
- references/plugin-currency.md 13 KB
- references/prose-pass.md 5.6 KB
- references/push-discipline.md 42 KB
- references/wildcat-marketplace.md 5.9 KB
- references/wildcat-overlays.md 4.5 KB
- references/wildcat-sources.md 2.5 KB
- references/xray-reuse.md 5.6 KB
- scripts/audit_synopsis.py 46 KB runs code
- scripts/check_wildcat_contributor.py 2.1 KB runs code
- scripts/hexctl.py 690 KB runs code
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.
- 4d ago Changed · +7 lines babe74b13895
- 6d ago Changed · +16 lines e45f16956427
- 7d ago Changed · +37 lines d30f98306483
- 8d ago Changed · +90 lines 809f4111662e
- 12d ago First seen · 825 lines · 78 tokens per session scan A 25091f0549b3
fiat is a skill published in the GitHub repository wildcat-finance/skills (12 stars, last pushed today), licensed Apache-2.0. It adds 78 tokens to every session and 17,163 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…