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 zgbrenner/agentcounsel --skill tax-cold-start-interviewgit clone --depth 1 https://github.com/zgbrenner/agentcounselWrote 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/zgbrenner/agentcounsel/tax-cold-start-interview)<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/tax-cold-start-interview"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/tax-cold-start-interview/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/zgbrenner/agentcounsel/tax-cold-start-interview"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/tax-cold-start-interview.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 | $0.00054 | $0.02524 |
| Opus 5 | $0.00027 | $0.01262 |
| Sonnet 5 | $0.00011 | $0.00505 |
| Haiku 4.5 | $0.00005 | $0.00252 |
Grade A, and why
Tax Cold-Start Interview 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 9d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tax Cold-Start Interview
Purpose
Conduct a structured, staged interview with a tax practice group — led by a supervising attorney or authorized designee — to gather the information required to populate practice-profiles/tax.md. The skill walks through all eight profile fields in sequence, records every answer, and assembles a filled draft of the profile for the practice group's review and approval. It produces draft legal work product for attorney review — not legal advice and not a final configuration.
Use When
- A team is adopting AgentCounsel and needs to configure
practice-profiles/tax.mdfor the first time. - A tax practice group is being onboarded to the library and no current profile exists.
- The library is being stood up for the first time and the tax area is included in scope.
- A practice group wishes to revisit or rebuild its profile from scratch rather than make incremental updates.
Required Inputs
- A knowledgeable person from the tax practice group — a supervising attorney or an authorized designee — who can answer questions about the group's jurisdiction, positions, escalation rules, and review requirements.
- Any existing playbooks, templates, source-of-truth documents, or standard-form documents the group already uses, so they can be referenced or cited in the profile.
Do Not Use When
- The group is actively working a live tax matter. This skill configures the library; it does not support an open matter.
- A
practice-profiles/tax.mdalready exists and is current. In that case this is a refresh, not a cold start — though the skill may still be used to rebuild the profile deliberately. - No authorized person is available to answer. Do not complete the interview with guessed or inferred answers; record all gaps as
[CONFIRM: ...]placeholders. - The purpose is to handle a specific tax matter (use the appropriate matter-level skill for that task).
Legal Safety Rules
- Produce draft legal work product for attorney review. This is not legal advice.
- Never guess or infer an answer to any interview question. If the interviewee cannot answer a question, record
[CONFIRM: answer required from practice group]and move on. - The filled profile is a draft. It must be reviewed and explicitly approved by the supervising attorney or practice group before it governs any AgentCounsel work product.
- Do not invent standard positions, clause preferences, escalation thresholds, or review rules. Record only what the interviewee provides.
- Do not include client-specific facts, client names, matter identifiers, or privileged details in the profile. The profile is a reusable group-level configuration, not a matter record.
- Do not state or imply that any threshold, position, or rule in the profile satisfies a legal requirement under any jurisdiction. Jurisdiction-specific legal obligations are for the attorney to verify.
- Flag every item the interviewee defers or leaves open with a visible
[CONFIRM: ...]placeholder so the reviewer can see exactly what is unresolved.
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.
- 9d ago First seen · 176 lines · 54 tokens per session scan A fd116e418644
Tax Cold-Start Interview is a skill published in the GitHub repository zgbrenner/agentcounsel (19 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 2,524 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
legal-research
A legal research skill for finding and analysing laws and court cases, including similar cases. It requires access to a reliable legal research database before producing a formal report.
document-fill
A document-filling assistant that uses a supplied template and case files to fill in forms, contracts, or legal documents. It also reports where each filled value came from and which details are missing.
contract-review
A contract-review workflow for agreements governed by Chinese law, United States law, or both. It examines clauses one by one and produces a list of legal-risk questions, with an optional marked-up Word document.
fedramp
Expert guidance for FedRAMP certification and compliance under CR26 (FedRAMP Consolidated Rules for 2026). Use this skill whenever a user asks about FedRAMP authorization, ATO (Authority to Operate), cloud security for federal government, NIST SP 800-53 controls, CSP compliance, or any of the core FedRAMP document…
eu-cra
Expert EU Cyber Resilience Act (CRA) advisor for Regulation (EU) 2024/2847 — mandatory cybersecurity and vulnerability handling requirements for all products with digital elements (PDEs) sold in the EU. Use this skill for gap analysis, product classification (Default / Class I / Class II), conformity assessment route…
aenderungsvorbehalt-308
Für Änderungsvorbehalt 308: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.