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 mikestangdevs/craft-skills --skill prove-every-numbergit clone --depth 1 https://github.com/mikestangdevs/craft-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/mikestangdevs/craft-skills/prove-every-number)<a href="https://agentmods.dev/skills/mikestangdevs/craft-skills/prove-every-number"><img src="https://agentmods.dev/badge/skills/mikestangdevs/craft-skills/prove-every-number/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/mikestangdevs/craft-skills/prove-every-number"><img src="https://agentmods.dev/badge/skills/mikestangdevs/craft-skills/prove-every-number.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 | $0.00153 | $0.01283 |
| Opus 5 | $0.00077 | $0.00642 |
| Sonnet 5 | $0.00031 | $0.00257 |
| Haiku 4.5 | $0.00015 | $0.00128 |
Grade A, and why
prove-every-number 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prove Every Number
The failure mode this fixes
An agent needs a value — a timeout, an efficiency factor, a retry limit, a price, a physical constant — and it makes one up that looks plausible. 0.95. 30. 1.2x. The code runs, the demo works, and the number sits there radiating false authority. Months later someone builds a real decision on output that was quietly resting on a guess.
The malignant variant: a test fails, and instead of finding out why, the agent adjusts the constant until it passes. Now the codebase contains a number whose only provenance is "this made the assertion green" — a lie sticker over a defect.
This skill enforces a simple provenance rule: every number is derived or cited. Derived means computed from real inputs or first principles, and the derivation is traceable. Cited means it points at something outside the code's own wishes — a spec, a datasheet, a standard, an RFC, a measured benchmark, a documented product decision. A number that is neither is a finding.
When to Use This Skill
- You (or the agent) are about to introduce a numeric literal that isn't 0, 1, or a structural index
- Reviewing AI-generated code for magic numbers and invented defaults
- A failing test was fixed by changing a constant, tolerance, or threshold
- Output feeds a real decision — money, capacity, safety, compliance, anything a customer reads
- Real input data exists but the code uses a hardcoded stand-in "for now"
Don't use when: the number is structurally meaningless (array index, test fixture ID, placeholder in a sketch you've labeled as a sketch). Don't demand a citation for MAX_RETRIES = 3 in a script nobody's life depends on — scale provenance rigor to how much the output gets trusted.
Instructions
1. Inventory the numbers
In the diff (or file), list every numeric literal and ask of each: where did this come from? Three acceptable answers: derived (show the derivation), cited (show the source), or explicitly-labeled assumption (see step 3). "It seemed reasonable" is the finding.
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 · 79 lines · 153 tokens per session scan A ecc417421dea
prove-every-number is a skill published in the GitHub repository mikestangdevs/craft-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 153 tokens to every session and 1,283 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
plumb-line-audit
Use when auditing a diff or repository against the plumb-line principles — finds laundered uncertainty, boundary leaks, hardcoded priors, overstated maturity, outputs lacking recorded lineage, and baseline drift with no explanation. Read-only: it reports, never auto-fixes.
Tech Debt Auditor
Identifies and prioritizes technical debt in a codebase with an effort/impact matrix.
craft-audit
The front door to the craft skills — a whole-project production-readiness orchestrator that drives the ten per-domain craft skills (ux, frontend, backend, db, security, infra, observability, testing, lint, ai) instead of auditing one surface at a time. It discovers the project's shape, plans an audit per surface, and…
craft-backend
The Craftsman standard for building and reviewing backend code — API routes, request validation, the authentication boundary, service/business logic, error handling, route rate-limit middleware, third-party integrations, and background jobs. Use this WHENEVER the work touches the server side: adding or reviewing a…
code-consolidation
This skill should be used when the user asks to "find duplicated code", "map responsibilities", "consolidate code", "find code sprawl", "analyze duplication", "create consolidation plan", or mentions "código duplicado", "responsabilidades espalhadas", "consolidar". Analyzes codebases to identify scattered…
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.