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/jamditis/claude-skills-journalismWrote 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/plugins/jamditis/claude-skills-journalism/dev-toolkit)<a href="https://agentmods.dev/plugins/jamditis/claude-skills-journalism/dev-toolkit"><img src="https://agentmods.dev/badge/plugins/jamditis/claude-skills-journalism/dev-toolkit/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/plugins/jamditis/claude-skills-journalism/dev-toolkit"><img src="https://agentmods.dev/badge/plugins/jamditis/claude-skills-journalism/dev-toolkit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dev-toolkit 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 17d 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.
What it actually says
{
"name": "dev-toolkit",
"version": "2.0.0",
"description": "Twelve development skills for newsroom and research dev teams: accessibility, context management, directed multi-agent execution, Electron, mobile debugging, Python pipelines, ethical scraping, no-build frontends, web UI craft, and CLAUDE.md maintenance.",
"author": {
"name": "Joe Amditis",
"email": "[email protected]"
}
}
What it installs
The manifest is a name and a version. 12 skills travel with it, and installing the plugin installs all of them — 380 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill web-scraping A 33 tokens
- Skill accessibility-compliance A 32 tokens
- Skill one-way-door A 29 tokens
- Skill python-pipeline A 26 tokens
- Skill electron-dev A 34 tokens
- Skill web-ui-best-practices A 32 tokens
- Skill zero-build-frontend A 34 tokens
- Skill claude-md-updater A 34 tokens
- Skill context-engineering-fundamentals A 32 tokens
- Skill vibe-coding A 35 tokens
- Skill director A 28 tokens
- Skill mobile-debugging B 31 tokens
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.
- 17d ago Changed b1436ea96362
- 1mo ago First seen · 10 lines scan A c998f9942a92
dev-toolkit is a plugin published in the GitHub repository jamditis/claude-skills-journalism (428 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
paper-discourse-graph
Audit LaTeX papers as discourse graphs for reader-state continuity, paragraph flow, planted/payoff questions, detours, and figure/equation placement.
rigorous-paper-author
Draft or revise mathematically rigorous LaTeX papers with claim graphs, notation ledgers, theorem discipline, and numerical-analysis rigor. Theory-heavy ML, scientific computing, numerical analysis, control, geometry, applied mathematics.
tikz-figure-review
Review and fix alignment, label collision, clipping, legend-over-data, and overlap issues in TikZ and pgfplots figures inside LaTeX documents.
plan-to-dag
Convert large multistep plans into dependency-aware DAGs with execution waves, parallel worksets, validation gates, and subagent-ready prompts.
contentforge
Content lifecycle system for TechShu delivery teams - 22 skills, 13 agents, 10-gate pipeline, 43-pattern AI humanizer, run auditor, real .docx output, and a measure-audit-plan loop that compounds per brand.
rebuttal-skills
Two composable Claude Code skills for writing peer-review rebuttals: write-rebuttal (overall process — Parikh–Batra–Lee method, 18 tactics, AC-facing structure) and nlp-rebuttal (per-concern playbook — 28 reviewer-concern scenarios with answer templates).