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 agentmods add skills/hoavdc/codexkit/codexkit-budget-variance-explainernpx skills add hoavdc/CodexKit --skill codexkit-budget-variance-explainergit clone --depth 1 https://github.com/hoavdc/CodexKitWhat 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 | $0.00080 | $0.00754 |
| Opus 5 | $0.00040 | $0.00377 |
| Sonnet 5 | $0.00016 | $0.00151 |
| Haiku 4.5 | $0.00008 | $0.00075 |
Grade A, and why
codexkit-budget-variance-explainer 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 2d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Budget Variance Explainer
Purpose
Make budget data understandable for non-finance managers so they can act on it.
When to use
- a team lead receives budget vs actual numbers and needs to understand them
- a department manager needs to explain their cost center to leadership
- monthly or quarterly financial reviews for non-finance stakeholders
- translating finance team output into operational language
When not to use
- technical accounting analysis or journal entries
- external audit preparation or regulatory reporting
- when the variance requires forensic investigation
Inputs
- budget vs actual data (table, spreadsheet extract, or raw numbers)
- time period (month, quarter, YTD)
- any known context (e.g. "we hired 2 extra people" or "project X was delayed")
- audience (team lead, VP, non-finance manager)
Procedure
- Identify the top 3–5 variances by absolute dollar impact.
- Classify each: favorable or unfavorable.
- Explain WHY each variance happened in one sentence (driver).
- Determine if the variance is one-time or recurring.
- Suggest what action to take for each significant variance.
- Write a 2-sentence headline summary suitable for an exec email.
- Produce an action table: driver → impact → owner → action.
Output
- headline summary (2 sentences)
- variance explanation table (line item, variance, driver, one-time/recurring, action)
- recommended talking points for presenting to leadership
Definition of done
- every variance > 5% is explained
- explanations use business language, not accounting jargon
- each significant variance has an owner and recommended action
- a non-finance person can understand the summary without follow-up questions
Examples
- "Explain why our department is $30K over budget this month in plain English."
- "Turn this spreadsheet into talking points for the VP meeting."
- "Our travel spend is 40% over plan — write an explanation and recommended action."
Quality Criteria
- Data sources and assumptions are explicitly stated
- Calculations are reproducible from provided inputs
- Visualizations or tables have clear labels, units, and time ranges
- Caveats and confidence levels are documented for estimates
What ships with it
1 file 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.
- 2d ago First seen · 88 lines · 80 tokens per session scan A e21c5fc676dc
codexkit-budget-variance-explainer is a skill published in the GitHub repository hoavdc/CodexKit (21 stars, last pushed 3mo ago), licensed MIT. It adds 80 tokens to every session and 754 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
data_analyst
Analyses datasets with professional rigour — statistical summaries, clear narratives, and well-chosen visualisations.
reducing-aigc-detection
Systematically reduce AIGC detection rates in academic papers (Chinese/English). Analyzes detection reports, identifies high-impact sections, applies multi-layer rewriting strategies preserving formatting/footnotes, and verifies results. Supports 维普/知网/Turnitin platforms.
defending-applications
Application security defense knowledge for builders. Covers Web/API/GraphQL hardening (XSS/SQLi/SSRF/IDOR/BOLA/Mass Assignment/deserialization/upload/path traversal), authentication/authorization (OAuth 2.0/OIDC/JWT/Session/Cookie/SAML/SSO), and LLM application security (prompt injection, jailbreak, RAG poisoning…
analyzing-security
Scans code for security vulnerabilities, detects dangerous patterns, and ensures security decisions are documented. Use when running security scans, auditing code, or checking for OWASP issues, injection risks, or sensitive data leaks. Automatically triggered on new modules, security-related changes, or post-refactor.
architecting-security
安全架构与治理：威胁建模 (STRIDE/PASTA/LINDDUN)、零信任身份架构、IAM/SSO/MFA/PAM、合规框架 (SOC2/PCI/HIPAA/GDPR)、DLP、隐私工程、安全控制设计。Use when designing security architecture, threat modeling new systems, implementing zero-trust identity, designing IAM/SSO/PAM, building compliance evidence chains, or planning privacy-by-design.
building-agent-systems
AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt injection, jailbreak defense, output filtering), RAG architecture (chunking, hybrid retrieval, rerank), and prompt…