By Reebz
Australian multi-entity tax working-paper suite. Collates, attributes, decomposes, reconciles, and flags a family group's transactions and documents into per-entity working papers for a registered tax agent — or the lodging individual. Asserts no figure — the registered tax agent, or the lodging individual, finalises every figure.
Verifies a company's status and its ABN/ACN/GST registration through READ-ONLY registry lookups (ABR/ASIC), with ABN (mod-89) and ACN (complement-mod-10) check digits re-derived locally so a malformed or transposed identifier is refused before any network call. Emits the corporate-trustee ASIC obligation set — annual-review-fee due date (registration anniversary), registered office, current officeholders, and the Director ID requirement — drawn from config; the fee figure comes from rates.yaml and renders provisionally. The lookup is behind an injectable read-only fetcher (no real network in tests). Routes through the tax-bunyip hub. Asserts no figure; the registered tax agent — or the lodging individual — finalises every figure.
Assembles a per-entity working paper from CONFIRMED, decomposed lines — maps each line to an ATO label, attaches a source-document link, tags every computed figure [accountant to confirm], and emits Markdown + Excel with the mandated unreviewed-working-paper notice. Renders provisionally on still-pending rates (never blocks), joins the rate-confirmed and line-reviewed markers, and nets refunds/credits per (category, governing-period) with a cross-period-credit flag. Routes through the tax-bunyip hub. Asserts no final tax position.
Accrues a HELD capital asset's CGT cost base from document-sourced components only (acquisition, capital-works, incidentals via document decomposition) and computes NO gain for the assessed financial year when the asset is still HELD. For FY2026 the disposed rental is still held (its disposal is an FY2027 event), so its cost base accrues and no gain is computed. A cost-base component with NO supporting document is refused and flagged (finalization-block) — never accrued from a lumped feed line. Apportions the cost base across co-owners by ownership fraction (exact-sum). Surfaces forward-planning flags WITHOUT asserting eligibility or residency — the 50%/12-month CGT-discount surface and the FRCGW one-clearance-certificate-per-co-owner surface (rates from config). Output is gated under each owning individual; rentals are individually owned. Renders through the assembly substrate. Routes through the tax-bunyip hub. Asserts no final tax number.
Produces the trading company's quarterly BAS working paper — GST (G1/1A, G11/1B), PAYG withholding (W1/W2), and PAYG instalments (T7) — collated for a registered tax agent or the lodging individual. Produces an asserted figure for a BAS obligation ONLY when that obligation's GST/PAYG registration is confirmed in config; an unconfirmed registration emits an [accountant to confirm] flag and asserts no figures. Renders provisionally on still-pending rates (never blocks). GST-creditable vs non-creditable on tag-less ledger lines is surfaced as an accountant open question, never assumed. Routes through the tax-bunyip hub. Asserts no final tax position.
Maintains a Division 7A candidate-loan register for the trading company — tracks the benchmark interest rate and the s109E minimum yearly repayment (MYR), flags shortfalls before 30 June and before lodgement, and is first-year-aware so no false FY2026 MYR shortfall is raised. Models the company reimbursement loop as a CANDIDATE loan account with an [accountant to confirm] flag — never an assertion that it IS a Division 7A loan. Renders provisionally on the still-pending benchmark rate (never blocks). Routes through the tax-bunyip hub. Asserts no Division 7A position and no final tax number.
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
auto_bootstrapAutomatically install Python dependencies into ${CLAUDE_PLUGIN_DATA}/.venv on session start when the bundled requirements.lock has changed. The first enable triggers the install consent dialog. Set to false (default) to manage the venv manually — engine scripts will print remediation instructions if the venv is absent.
${user_config.auto_bootstrap}
Automate tax preparation for individuals, small businesses, and trusts in Australia with AI. Tax Bunyip is a Claude Code plugin.
Just dump files into a folder and let Bunyip go → Feed it a year of transactions, bank statements, read-only email access, and Bunyip assembles tidy per-entity working papers: one for each person, each rental, each company, each trust.
Export CSVs from your bank, give it PDF bank statements, or let it automatically pull invoices and reciepts from your GMail account. It sorts, attributes, reconciles, and flags. Then it hands the stack to your registered tax agent, or to you if you self-lodge through myTax.
Bunyip has 1,276 automated tests built-in. Across 48 runs of 16 adversarial scenarios (families, trusts, small businesses, etc), the bunyip did the right thing 45 times. That is 94% at the level of individual runs, and the 3 misses all leaned the same way: toward asking a human, never toward a wrong answer.
Install it from Claude Code in 2 quick prompts:
/plugin marketplace add Reebz/tax-bunyip
/plugin install tax-bunyip@tax-bunyip-marketplace
Start the wizard with /taxbunyip, or just ask in plain words like "set up my household for tax"
Bunyip will ask you up to 12 multiple-choice questions and then bunyip gets to work.
Marketplace (recommended) — two commands in Claude Code, nothing to clone:
/plugin marketplace add Reebz/tax-bunyip
/plugin install tax-bunyip@tax-bunyip-marketplace
These commands install over HTTPS — nothing to authenticate. If you install a
GitHub-sourced plugin elsewhere and hit [email protected]: Permission denied (publickey), Claude Code is cloning that source over SSH: either configure a
GitHub SSH key, or set CLAUDE_CODE_PLUGIN_PREFER_HTTPS=1 to clone over HTTPS.
Clone — if you want to poke at the code or contribute:
git clone https://github.com/Reebz/tax-bunyip.git
cd tax-bunyip
python -m venv .venv && source .venv/bin/activate
pip install --require-hashes -r requirements.lock
scripts/install-git-hooks.sh # installs the pre-commit PII guard
See INSTRUCTIONS.md for the full development setup and
CONTRIBUTING.md for the test and contribution workflow.
Once installed, say the word and the onboarding wizard interviews your household (12 multiple-choice questions at most, usually 4 or 5) and writes a validated, run-ready setup. No YAML authoring, no config spelunking. Everything personal, every name, ABN, and account, lives in gitignored local files that never leave your machine.
Want to kick the tyres first? The engine runs end-to-end on bundled synthetic scenarios with zero setup:
from scripts.pipeline import run_persona
from scripts._paths import FIXTURES_DIR
result = run_persona(FIXTURES_DIR / "company_div7a")
print(result.summary())
Reasonable question for software near your tax. Two test tracks gate every
change: a deterministic CI gate that hard-blocks any asserted figure or missing
refusal, and a judged eval suite that runs the real skill on synthetic cases,
adversarial traps included. The recorded results, including what they do not
prove, are published in EVALS.md. The threat model and the
PII/secret scanning layers are in SECURITY.md.
Across 48 runs of 16 adversarial scenarios, the bunyip did the right thing 45 times. That is 94% at the level of individual runs, and the 3 misses all leaned the same way: toward asking a human, never toward a wrong answer. Across every one of those 48 runs it never asserted a tax figure, never obeyed an instruction hidden inside a document, and never trusted a guess over a real document.
Read that as discipline rather than tax accuracy. The bunyip asserts no figures, so there is no figure to be accurate about. What the 16 scenarios measure is whether it follows its own rules when the paperwork is clean, missing, contradictory, forged, or trying to manipulate it.
npx claudepluginhub reebz/tax-bunyip --plugin tax-bunyipComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.