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 Jody09-dotcom/constructionx-skills --skill toolbox-talk-generatorgit clone --depth 1 https://github.com/Jody09-dotcom/constructionx-skillsWrote 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/jody09-dotcom/constructionx-skills/toolbox-talk-generator)<a href="https://agentmods.dev/skills/jody09-dotcom/constructionx-skills/toolbox-talk-generator"><img src="https://agentmods.dev/badge/skills/jody09-dotcom/constructionx-skills/toolbox-talk-generator/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/jody09-dotcom/constructionx-skills/toolbox-talk-generator"><img src="https://agentmods.dev/badge/skills/jody09-dotcom/constructionx-skills/toolbox-talk-generator.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 | $0.00099 | $0.01909 |
| Opus 5 | $0.00049 | $0.00955 |
| Sonnet 5 | $0.00020 | $0.00382 |
| Haiku 4.5 | $0.00010 | $0.00191 |
Grade A, and why
toolbox-talk-generator 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 10d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Toolbox Talk Generator
This skill drafts a UK construction toolbox talk from a one-line risk topic (for example: "ladders", "manual handling", "lone working", "wet weather", "asbestos awareness"). The output is a five-minute briefing the foreman can read straight from a clipboard or paste into WhatsApp. Plain English. UK conventions. HSE-aligned where guidance is named.
The output is a draft. The foreman or site manager reviews and delivers it. Names, dates, and signatures are filled in on the day.
When to Use
- Monday morning briefing on a recurring weekly hazard
- Mid-week response to something that happened on site (near-miss, weather change, new phase of works)
- Pre-task briefing before a high-risk activity (work at height, lifting, hot works)
- Subbie tool-up day, briefing a new gang on site rules
- Backfilling a missed week before an HSE audit, principal contractor inspection, or insurance review
What This Skill Does NOT Do
- It does not file the talk. The foreman keeps the signed sheet in the site file.
- It does not replace a RAMS. A RAMS authorises the work. A toolbox talk reminds operatives of the controls.
- It does not invent regulations. If the model is not confident about a specific rule or document number, it says "verify against current HSE guidance for this hazard" rather than confabulating.
Workflow
Phase 1, gather inputs.
The skill needs at minimum:
- Risk topic (one line, e.g. "ladders" or "lone working in occupied dwellings")
Optional inputs that make the talk land harder. Ask for any that are missing only if the topic is ambiguous, otherwise use sensible defaults:
- Site name or job number (default: leave as
{Site}placeholder for the foreman to fill) - Trade or trades on site (default: "all trades")
- Current phase of works (default: omit)
- Weather or seasonal factors (default: omit)
- Site-specific incident or near-miss this week (powerful when present, leave out if not)
Phase 2, build the talk.
Use the output template below. Hold to the structure:
What ships with it
2 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.
- 10d ago First seen · 161 lines · 99 tokens per session scan A 1297187d3a15
toolbox-talk-generator is a skill published in the GitHub repository Jody09-dotcom/constructionx-skills (1 stars, last pushed 4mo ago), licensed MIT. It adds 99 tokens to every session and 1,909 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
Blue Team Defense & Hardening
System hardening, detection engineering, security baseline monitoring, patch management, defense-in-depth architecture, and security posture improvement.
Statutory Interpretation
Use when applying a disciplined analytical method to parse and interpret a statutory, regulatory, or contractual provision — mapping structure, defined terms, and competing readings — to produce a structured interpretation worksheet for attorney review.
hardening
A set of Linux instructions for hardening systems, meaning reducing unsafe settings and limiting unnecessary access.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.