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/bromso/metapowers/variancenpx skills add bromso/metapowers --skill variancegit clone --depth 1 https://github.com/bromso/metapowersWrote 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/bromso/metapowers/variance)<a href="https://agentmods.dev/skills/bromso/metapowers/variance"><img src="https://agentmods.dev/badge/skills/bromso/metapowers/variance.svg" alt="Measured on agentmods" 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 | $0.00008 | $0.00437 |
| Opus 5 | $0.00004 | $0.00218 |
| Sonnet 5 | $0.00002 | $0.00087 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
variance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Variance
Perform variance analysis for "$ARGUMENTS". Compare actual results to budget, forecast, or prior period and explain the differences.
Prerequisites
None — utility skill, run anytime. More effective when financial data is available from Phase 7 (statements) or Phase 4 (trial balance).
Process
-
Establish comparison basis:
- What are we comparing? (actual vs. budget, actual vs. forecast, actual vs. prior period)
- What level of detail? (total entity, department, account, line item)
- What period? (month, quarter, year)
-
Calculate variances:
- For each line item, compute:
- Dollar variance — actual minus budget/forecast
- Percentage variance — dollar variance divided by budget/forecast
- Classify as favorable (F) or unfavorable (U)
- Highlight variances exceeding materiality thresholds
- For each line item, compute:
-
Analyze root causes:
- For each significant variance, identify the driver:
- Volume variance (more or fewer units)
- Price variance (higher or lower unit cost/price)
- Mix variance (different product/service mix)
- Timing variance (recognized in a different period)
- One-time items (non-recurring events)
- Quantify each driver where possible
- For each significant variance, identify the driver:
-
Write the artifact to
.metapowers/accounting/$ARGUMENTS/variance.mdwith sections:- Variance Summary — high-level overview of actual vs. budget with key metrics
- Detailed Variance Table — line-by-line comparison with dollar and percentage variances
- Root Cause Analysis — explanation of significant variances
- Recommendations — actions to address unfavorable variances or capitalize on favorable ones
Output
The variance analysis written to .metapowers/accounting/$ARGUMENTS/variance.md. Present a summary highlighting:
- Top favorable and unfavorable variances
- Key root causes identified
- Recommended actions
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 First seen · 48 lines · 8 tokens per session scan A 03049d9d7198
variance is a skill published in the GitHub repository bromso/metapowers (1 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 437 once invoked, about $0.0000 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
laravel-stripe-connect
Use when implementing multi-vendor marketplace payments, seller onboarding, commissions, payouts, or split payments with Stripe Connect.
invest
First-time fork users: run the invest-setup skill first to initialize. The main flow lives in this skill (the AI agent uses the CLI/MCP to view the portfolio / run the committee / replay decision history). The Web GUI has been retired (2026-07) — every capability is exposed via CLI subcommands / MCP tools. The backend…
invest-backup
Back up / restore openInvest's local state — memory/ (holdings, strategy, user profile, committee records, dream logs) + db/ (trade ledger, job run history, market-data cache) + .env (SMTP/API credentials) + userprofile.json. All of this data is .gitignore'd with no historical versions in git, so a single accidental…
building
Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.
plan-review-gate
Use after saving a non-trivial plan or decision RFC when a fail-closed feasibility, completeness, and alignment review must block execution.
cc10x-guide
Answers questions about cc10x itself — what it is, how to install and configure it, how the router, workflows, memory, and hooks operate, and how to troubleshoot. Use this skill when: the user asks ABOUT cc10x — "what is cc10x", "how do I configure cc10x", "why isn't cc10x activating", "how do cc10x workflows work"…