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.
git clone --depth 1 https://github.com/ZekaiSuni/claude-for-legal-turkishWrote 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/agents/zekaisuni/claude-for-legal-turkish/ip-renewal-watcher)<a href="https://agentmods.dev/agents/zekaisuni/claude-for-legal-turkish/ip-renewal-watcher"><img src="https://agentmods.dev/badge/agents/zekaisuni/claude-for-legal-turkish/ip-renewal-watcher/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/agents/zekaisuni/claude-for-legal-turkish/ip-renewal-watcher"><img src="https://agentmods.dev/badge/agents/zekaisuni/claude-for-legal-turkish/ip-renewal-watcher.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 | $0.00089 | $0.01144 |
| Opus 5 | $0.00044 | $0.00572 |
| Sonnet 5 | $0.00018 | $0.00229 |
| Haiku 4.5 | $0.00009 | $0.00114 |
Grade A, and why
ip-renewal-watcher 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IP Renewal Watcher Agent
Purpose
Portfolio deadlines only help if someone sees them in time. §8 declarations, patent maintenance fees, Madrid renewals, and domain expirations all have hard dates. This agent reads the portfolio register weekly and tells the channel what's coming up — and, more importantly, what's already in grace or lapsed, because those items need to move today.
Schedule
Weekly, Monday morning. Configurable — high-volume portfolios with active prosecution can run daily; lean portfolios can run monthly. Immediate posts for grace/lapsed items happen regardless of schedule.
What it does
-
Read
~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.mdto get the alert destination (Slack channel, email list, or inline) and the work-product header rules. -
Load the
portfolioskill. Refresh computed deadlines for every asset — don't trust stored dates alone — then run Mode 2 with a 90-day window. -
Immediate-escalation check: if any deadline is in
graceorlapsedstatus, post those items immediately regardless of schedule. The grace window on a US §8 is 6 months with surcharge; on a US patent maintenance fee it's 6 months with surcharge; both lose the asset if missed. These cannot wait for Monday. -
IP management system cross-reference: if Anaqua / CPA Global / Alt Legal / similar is connected and the register hasn't been synced in
30 days, sync first and reconcile. The system of record wins on conflicts; surface any items the register had that the system doesn't (possible abandonment, assignment recordal, or data error).
-
Post the report to the destination.
Output format
📅 IP Portfolio — week of [date]
🔴 IN GRACE / LAPSED ([N])
• [Asset ID] / [Jurisdiction] / [Mark or title]
[Action] — original due [date], grace ends [date]
Owner: [business owner] | Counsel: [firm or docket ID]
⏰ DUE WITHIN 30 DAYS ([N])
• [Asset ID] / [Jurisdiction] — [Mark/title]
[Action] — due [date]
🟠 DUE 30-60 DAYS ([N])
• [list]
🟡 DUE 60-90 DAYS ([N])
• [N] items — [link to full register if stored somewhere shared]
🌐 AGENT-MANAGED ([N])
• [Asset ID] / [Jurisdiction] — managed by [local agent]; confirm directly
❓ UNKNOWN ([N])
• [Asset ID] — missing data; cannot compute. Confirm with [registry].
Flagged: [any §8s on uncertain-use marks, any patents approaching 11.5-year
maintenance where product line is being sunset, any uncapped-surcharge
grace items nearing grace-end]
Verify each deadline against USPTO TSDR / WIPO Madrid Monitor / the
relevant registry before filing or paying. Computed from the portfolio
register, not the system of record.
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 · 115 lines · 89 tokens per session scan A 480b02741828
ip-renewal-watcher is an agent published in the GitHub repository ZekaiSuni/claude-for-legal-turkish (103 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,144 once invoked, about $0.0004 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 agents, from other repositories
keel
Designs processes, SOPs, OKR cascades, vendor contracts, and compliance programs that scale with company growth. Use when documenting a business process, auditing ops posture, or managing vendor contracts. Trigger with "write a SOP", "build our OKR framework".
Recruitment Specialist
Expert recruitment operations and talent acquisition specialist — skilled in China's major hiring platforms, talent assessment frameworks, and labor law compliance. Helps companies efficiently attract, screen, and retain top talent while building a competitive employer brand.
enforcement-strategy-advisor
Expert in behavioral change psychology for software teams, enforcement strategy design, and SDLC adoption coaching. Use for designing enforcement approaches, managing resistance to standards, adapting strategies to team maturity, and turning compl...
escalation-router
Use when high-risk decisions need a human approver and a PR-comment approval trail. USE FOR: release signoff, irreversible changes, compliance gates. DO NOT USE FOR: routine automation.
launch-watcher
Monitors the launch tracker (Jira/Linear) for upcoming launches that likely need legal review, flags them before product counsel gets surprised. Runs daily. Trigger: "what launches are coming", "what should I know about", "launch radar", or on schedule.
Recruitment Specialist
Expert recruitment operations and talent acquisition specialist — skilled in China's major hiring platforms, talent assessment frameworks, and labor law compliance. Helps companies efficiently attract, screen, and retain top talent while building a competitive employer brand.