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 anton-abyzov/vskill --skill tax-filinggit clone --depth 1 https://github.com/anton-abyzov/vskillWrote 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/anton-abyzov/vskill/tax-filing)<a href="https://agentmods.dev/skills/anton-abyzov/vskill/tax-filing"><img src="https://agentmods.dev/badge/skills/anton-abyzov/vskill/tax-filing/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/anton-abyzov/vskill/tax-filing"><img src="https://agentmods.dev/badge/skills/anton-abyzov/vskill/tax-filing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 235 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00185 | $0.02871 |
| Opus 5 | $0.00093 | $0.01435 |
| Sonnet 5 | $0.00037 | $0.00574 |
| Haiku 4.5 | $0.00018 | $0.00287 |
Grade B, and why
tax-filing scanned grade B with 1 finding 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- Never tell the user to "wait for 1095-C" -- it's not needed for filing How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tax Filing Skill
Automates the entire tax preparation workflow for a small business (C-Corp, S-Corp, or LLC) and the owner's personal return. Built from real-world experience preparing a Delaware C-Corporation Form 1120 and MFJ Form 1040 with three children.
How This Skill Works
Tax preparation is a 7-phase pipeline. Each phase builds on the previous one. Run phases in order, but use parallel sub-agents within each phase to maximize speed.
Phase 1: Data Gathering
Launch these 5 research agents in parallel:
Agent 1: Accounting System Export
- If Xero: use the Xero API (OAuth2 custom connection) to export all data
- Settings: organization, chart of accounts, tax rates, contacts
- Per-year: bank transactions, journals, invoices, payments, reports (P&L, balance sheet, trial balance, bank summary)
- Note: bank STATEMENT LINES (unreconciled items in Xero UI) are NOT accessible via API -- only matched transactions
- If no accounting system: skip to bank statement analysis
Agent 2: Obsidian Vault Search
- Auto-discover vault: check
~/Projects/Obsidian/*/or common locations - Search for: tax, filing, 1099, W-2, P&L, accountant name, company name, EIN, EFTPS
- Read all synthesis docs in
wiki/synthesis/tax-* - Extract: credentials (EFTPS, accountant portal), prior research, income flow maps, bank analyses
- Check for prior year preparation documents
Agent 3: Gmail Search
- Search for accountant correspondence (extension status, appointment details, portal links)
- Search for tax forms: W-2 notifications (ADP, Gusto), 1099 (Ascen, KForce, Robinhood, BofA), 1095-C
- Search for: Xero invoices, Hetzner/Cloudflare/hosting invoices, bank connection notifications
- Search for Delaware franchise tax correspondence
- Extract: meeting dates, deadlines, payment confirmations, document statuses
Agent 4: Google Drive / Filesystem Search
- Auto-discover Google Drive mount:
~/Library/CloudStorage/GoogleDrive-*/My Drive/ - Search for organized tax folder (e.g.,
Finance-&-Legal/Tax/{year}-Tax-Filing/) - Inventory: W-2 PDFs, 1099 PDFs, bank statements, prior returns, invoices, contracts
- Also check
~/Downloads/for recently downloaded tax files - Read the prior year's filed corporate return (Form 1120) to understand how the accountant structured categories
What ships with it
4 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.
- 11d ago First seen · 238 lines · 185 tokens per session scan B 3ccb67302142
tax-filing is a skill published in the GitHub repository anton-abyzov/vskill (45 stars, last pushed 3d ago), licensed MIT. It adds 185 tokens to every session and 2,871 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
prereview
Review the current diff against this team's conventions and invariants before it ships. Invoke with /prereview before opening a PR, or run as a pre-push gate.
optimize-skill-loop
Deterministic outer-loop optimizer for a skill that already carries a frozen eval (produced upstream by an eval source such as create-skill-eval). Runs the frozen eval across user-chosen agents on fresh headless sessions via a pluggable adapter, grades quality/cost/perf, keeps the pareto-best variant, and versions…
create-skill-eval
Author a frozen, graded eval harness for ONE inner skill and freeze it inside that skill as a conformant eval/ directory (scenarios + deterministic evaluator + rubric + fixtures + HARNESS.md manifest). The eval content is skill-specific; this skill is the reusable methodology that produces it. Its output is consumed…
onboard-skills
Discovers and installs agent skills into a project (or the user-global lane) with the qvr CLI, where qvr.toml declares intent and qvr.lock is the resolved source of truth for what loads. Use when a user wants to find, add, register, or install skills from a skills registry or GitHub repo with qvr — e.g. "register a…
reproduce-skill-env
Reproduces an exact agent-skill set across machines, teammates, and CI using qvr's portable manifest and lockfile guarantees. Use when a user wants to share, pin, replicate, or CI-gate their qvr skills — e.g. "export my skills", "import this skill manifest", "pin everything to exact commits", "make skills…
fork-and-publish-skill
Customizes an installed agent skill and ships it back upstream or as a versioned fork using qvr's edit/publish authoring loop. Use when a user wants to modify, customize, fork, release, or publish a qvr skill — e.g. "edit this skill", "publish my changes", "fork a skill to my own repo", "cut a v1.0.0 release of a…