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 deciqAI/knowledge-skills --skill margin-of-safetygit clone --depth 1 https://github.com/deciqAI/knowledge-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/deciqai/knowledge-skills/margin-of-safety)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/margin-of-safety"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/margin-of-safety/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/deciqai/knowledge-skills/margin-of-safety"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/margin-of-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00138 | $0.01992 |
| Opus 5 | $0.00069 | $0.00996 |
| Sonnet 5 | $0.00028 | $0.00398 |
| Haiku 4.5 | $0.00014 | $0.00199 |
Grade A, and why
margin-of-safety 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 9d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Margin of Safety
Overview
Benjamin Graham introduced margin of safety in Security Analysis (1934) as the founding principle of value investing: buy assets at prices substantially below your estimate of intrinsic value so that estimation errors and adverse events don't produce permanent loss. The principle generalizes to engineering load factors, project budgets, founder runway, and any commitment where your estimate could be wrong.
The unifying insight: point estimates are systematically optimistic. Margin of safety is the structural discipline that survives that optimism.
Composes with antifragile (margin = bounded-downside half), black-swan (margin is what survives the tail you didn't predict), expected-value-and-kelly (margin sizing relates to Kelly fractional-betting), and first-principles (audit the estimate first; then apply margin).
When to Use
- Sizing any commitment under uncertainty: investment positions, project budgets, fundraising timelines, hiring plans, capacity reservations
- A point estimate is being used as the basis for a major decision
- "Just-in-time" or "lean" or "fully utilized" pressure is removing buffers from a critical system
- A historically reliable system has been gradually de-buffered until it operates at the edge
- Weighing whether a stretched valuation leaves any buffer — AI capex assumptions, AI-era valuations, or whether a price already extrapolates optimistic AI adoption
- Someone says: "margin of safety," "Ben Graham," "value investing," "buffer," "load factor," "buy a dollar for fifty cents," "Mr. Market"
Not when: the domain is genuinely deterministic with no estimation error (rare); the cost of the buffer exceeds the expected loss from going without; you are using margin as an excuse to avoid any commitment ("perpetual margin" is procrastination).
Coaching Novices (Adaptive Front Door)
What ships with it
3 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.
- 9d ago First seen · 126 lines · 138 tokens per session scan A 1297c34eb070
margin-of-safety is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 138 tokens to every session and 1,992 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
invoice-chase
Runs collections on late invoices: builds an aging ladder (current/30/60/90+), assigns each invoice a rung on an escalation sequence with ready-to-send emails — friendly nudge, firm reminder with late-fee mention, final notice — plus a phone script, tone rules that preserve the relationship, a chase log, and…
audit-support
Gets the books audit-ready: builds the PBC (prepared-by-client) list by area, drafts walkthrough narratives for key cycles (revenue, purchases, payroll), matches auditor samples to support, prepares tie-out schedules, tracks open items with owners and due dates, and drafts responses to findings. Use when the user says…
financial-statements
Builds a full statement set — P&L, balance sheet, and indirect cash flow — from a trial balance or transaction export, mapping accounts to a standard chart and proving every tie-out in code. Use when the user says 'build a P&L from this trial balance', 'turn this export into financials', 'I need a balance sheet for…
plan-payroll
Plans payroll cash: true loaded cost per hire (gross plus employer taxes, benefits, tools), a payroll calendar with cutoffs and cash-out dates, a scenario table for new hire vs raise vs contractor-vs-employee, and a payroll-to-revenue check against rough industry bands. Use when the user asks "can I afford to hire"…
review-contract
Clause-by-clause contract review — inventories key clauses (term, termination, liability cap, indemnity, IP, payment, confidentiality, governing law, auto-renewal), flags deviations from market-standard positions with RED/YELLOW/GREEN severity and verbatim quotes, drafts redline language, and sets negotiation…
tax-prep
Organizes tax season — an organizer, not tax advice: a document checklist by category (income, expenses, assets, payroll, prior filings), an expense-category sweep that flags plausibly missed deductions in generic jurisdiction-agnostic categories, a quarterly-estimate calendar template, a clean handoff pack for the…