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 jeremylongworth-source/AgentSkills --skill variance-commentarygit clone --depth 1 https://github.com/jeremylongworth-source/AgentSkillsWrote 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/jeremylongworth-source/agentskills/variance-commentary)<a href="https://agentmods.dev/skills/jeremylongworth-source/agentskills/variance-commentary"><img src="https://agentmods.dev/badge/skills/jeremylongworth-source/agentskills/variance-commentary/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/jeremylongworth-source/agentskills/variance-commentary"><img src="https://agentmods.dev/badge/skills/jeremylongworth-source/agentskills/variance-commentary.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 | $0.00059 | $0.00338 |
| Opus 5 | $0.00030 | $0.00169 |
| Sonnet 5 | $0.00012 | $0.00068 |
| Haiku 4.5 | $0.00006 | $0.00034 |
Grade A, and why
variance-commentary 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 7d 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 Commentary
Core Workflow
- Identify actuals, target or baseline, period, scope, owner, and materiality threshold.
- Verify the variance calculation and units from supplied data.
- Break variance into volume, price, mix, timing, data quality, one-time, and operational drivers when evidence supports it.
- Separate confirmed drivers from hypotheses and required follow-up.
- State business impact, confidence, owner, and recommended next action.
- Keep reviewer notes separate from external or board-facing language.
Safety Rules
- Do not invent actuals, targets, forecasts, drivers, or accounting treatment.
- Do not provide tax, audit, accounting, legal, or investment advice.
- Do not publish finance commentary without finance owner review.
- Escalate material, unexplained, compliance-sensitive, compensation-related, or external-reporting variances.
Deliverable Shape
For variance commentary, provide:
- Variance summary
- Actual, baseline, and period
- Materiality assessment
- Driver breakdown
- Confidence and caveats
- Owner or follow-up
- Draft commentary for review
References
- Read
references/variance-commentary-checklist.mdwhen preparing finance, KPI, forecast, budget, revenue, or performance variance commentary.
What ships with it
2 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.
- 7d ago First seen · 44 lines · 59 tokens per session scan A 7aada33a6dd2
variance-commentary is a skill published in the GitHub repository jeremylongworth-source/AgentSkills (1 stars, last pushed 9d ago), licensed MIT. It adds 59 tokens to every session and 338 once invoked, about $0.0003 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
tb-bar-strategy
Use when generating, modifying, explaining, or reviewing TBQ3 Bar-based trading strategies with OnBar, OnInit, OnReady, entries, exits, MarketPosition, stop profit/loss, sizing, slippage, commission, multi-symbol, or cross-period logic.
tb-core
Use when working with TBQ3 or TB language code, including strategy generation, syntax questions, trading functions, Bar strategies, event-driven trading, Plot drawing, examples, or TB-specific code review.
tb-review
Use when reviewing, debugging, or improving TBQ3/TB language code for trading correctness, Bar strategy behavior, order direction, position state, sizing, costs, backtest realism, event timing, multi-symbol logic, or function documentation consistency.
setup-tradeblazer
Use after installing tradeblazerskills to collect user preferences for TBQ3/TB language work, including task focus, strategy type, document output location, and review expectations.
ve-midnight-editorial
OpenDesign's financial review: runway, burn, and the sustainability plan that keeps the project independent. Built as a decision-grade data & finance deck for board, leadership.
fs-creative-voltage
OpenDesign's seed pitch: the open, local alternative to closed AI design — why now, the wedge, and the ask. Built as a decision-grade fundraising pitch deck for pre-seed & seed VCs.