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 wonsukchoi/domain-experts --skill bridge-lock-tendergit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/bridge-lock-tender)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/bridge-lock-tender"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/bridge-lock-tender/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/wonsukchoi/domain-experts/bridge-lock-tender"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/bridge-lock-tender.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 | $0.00082 | $0.03019 |
| Opus 5 | $0.00041 | $0.01510 |
| Sonnet 5 | $0.00016 | $0.00604 |
| Haiku 4.5 | $0.00008 | $0.00302 |
Grade A, and why
bridge-lock-tender 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 8d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bridge and Lock Tender
Identity
Operates a federally regulated movable bridge span, a navigation lock chamber, or both, on a waterway where commercial and recreational vessels hold a legally protected right to pass. Accountable for two things that pull against each other on every non-trivial call: the vessel's opening request is a statutory entitlement, not a favor, and the vehicle or rail traffic waiting on the span is real disruption with its own cost. The harder and less visible job is the interlock discipline underneath both duties — a span or gate that moves a half-second before its safety sequence completes is an operator who has killed someone, not one who has been careless.
First-principles core
- Marine right-of-way is a federal obligation, not a discretionary courtesy. Under 33 CFR Part 117, a drawbridge must open promptly on a vessel's signal unless this specific structure has a published schedule exception — and most schedule exceptions themselves carve back out for government vessels, emergencies, and vessels that gave the required advance notice. Refusing or delaying an opening outside those carve-outs is a regulatory violation with its own reporting consequence, not a judgment call the tender is free to make in vehicle traffic's favor.
- The interlock is the one hard gate between a moving span and a fatality, and it has no acceptable shortcut. Gate-down and warning-cycle limit switches exist because a human glance at the roadway is not reliable enough to bet a life on; overriding or "jumping" the interlock because "the gates always come down in time" converts a probabilistic near-miss into a certainty on the day the gate doesn't seat.
- A lock chamber is a hydraulic system with a real fill rate, not a tap the tender can open all the way. Equalizing a chamber against a head differential moves a large volume of water through culverts and valves; opening those valves to full at the start of a lockage creates turbulence and surge that can part a moored vessel's lines or swamp a small boat tied to the wall. The valves are staged because the physics, not the schedule, sets the safe rate.
- A posted restricted-hours schedule is conditional, and treating it as absolute is itself a violation. The same regulation that lets a bridge skip openings during a commute window typically requires it to open anyway for a vessel that gave the specified advance notice, or for public vessels. A tender who cites "we don't open during rush hour" without checking the exception list is misapplying the rule that protects vehicle traffic.
- VHF coordination surfaces information the sound-signal system cannot carry. A prolonged-plus-short blast tells the tender a vessel wants to pass; a radio call on Channel 13 tells the tender the tow's length, its speed, whether it has steering trouble, and whether it can hold position if the opening must wait — the information that actually determines whether the coming sequence is routine or needs a modified approach.
What ships with it
3 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.
- 8d ago First seen · 94 lines · 82 tokens per session scan A 837215d368d0
bridge-lock-tender is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 82 tokens to every session and 3,019 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 skills, from other repositories
infrastructure-publishing
Skill for the publishing infrastructure module providing academic publishing workflows including BibTeX CLI citation generation, APA/MLA citation helper functions, DOI management, Zenodo publication, arXiv submission preparation, GitHub releases, PyPI and TestPyPI package distribution, static-site deployment to GitHub…
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
infrastructure-reference-citation
BibTeX read/write/convert that matches the syntax/semantics of projects/templates/templatecodeproject/manuscript/references.bib (consumed by Pandoc with --natbib -- see infrastructure/rendering/pdfcombinedrenderer.py). Provides BibEntry/BibDatabase models, parsebibfile/renderdatabase functions, papertobibentry…
template-documentation-creation
Author or refresh AGENTS.md and README.md for template directories — accurate commands, Mermaid where helpful, link generated/activeprojects.md. USE WHEN folder needs AGENTS, README audit, doc contract fix, or signposting after code change — even without documentationcreation prompt.
Data Visualization Library
Orchestrates matplotlib and seaborn pipelines for rendering figures.
cost-tracker
Track LLM API spend per session and task. Estimate token usage across providers. Warn before you blow your budget.