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 LandonSchropp/agent-toolkit --skill write-skillgit clone --depth 1 https://github.com/LandonSchropp/agent-toolkitWrote 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/landonschropp/agent-toolkit/write-skill)<a href="https://agentmods.dev/skills/landonschropp/agent-toolkit/write-skill"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/write-skill/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/landonschropp/agent-toolkit/write-skill"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/write-skill.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 | $0.00053 | $0.00804 |
| Opus 5.5 | $0.00021 | $0.00322 |
| Sonnet 5.5 | $0.00011 | $0.00161 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
write-skill 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 15d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Understand Requirements First
When asked to create or edit a skill:
-
If helpful, ask clarifying questions about the skill's purpose:
- What specific problem does this skill solve?
- What should the output/outcome be?
- What context or inputs will the skill work with?
- What are the key behaviors or patterns it should enforce?
-
Summarize your understanding and get user confirmation:
- "Let me confirm: this skill should [summary]. Is this correct?"
- Wait for user approval before proceeding
You cannot create a good skill without understanding what you're building.
New Plugins
A skill in a new plugin stays invisible until the plugin is registered and enabled, so land that first, as its own commit, before writing the skill:
- Add
plugins/<plugin>/.claude-plugin/plugin.jsonand the plugin's entry in the repository's root.claude-plugin/marketplace.json. - Enable it in both Claude Code settings files,
~/.dotfiles/tag-personal/claude/settings.jsonand~/.dotfiles/tag-work/claude/settings.json, as"<plugin>@landonschropp": true. Missing one leaves the plugin working on only half the machines.
The dotfiles are a separate repository, so that step lands there. Claude Code reads the setting at startup, so the new skill only appears in sessions opened afterwards.
Testing
After writing a skill, ask the user: "Would you like me to test the skill?" (Skills are often manually tested by the user, or can't be tested in an automated way, so you should ask before proceeding.)
If the user opts for the agent to test the skill:
- Design a scenario that exercises the skill's core purpose. Describe it to the user and get approval before running it.
- Run the scenario with a subagent. Document exactly what the agent did—what choices it made, what worked, what didn't.
- If the agent failed or rationalized away the skill's intent, identify the gap, add an explicit counter to the skill, and re-test.
- Repeat until the skill reliably produces the intended behavior.
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.
- 15d ago Changed · +2 lines 1b04f933b7d3
- 1mo ago Changed · +1 lines · +4 tokens per session b3faa2492075
- 1mo ago First seen · 59 lines · 49 tokens per session scan A 086b631b1194
write-skill is a skill published in the GitHub repository LandonSchropp/agent-toolkit (3 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 804 once invoked, about $0.0002 per session on Opus 5.5. 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
cf-cli
Cloudflare's official cf CLI (beta) for the public Cloudflare API and Workers projects. Use for finding and running Cloudflare commands from the terminal — sign-in and profiles, cf cli search, cf schema, cf deploy/dev/build, resource commands for DNS, zones, D1, KV, and R2 — and for choosing between cf and Wrangler in…
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
find-journalists
Build a researched, fit-checked journalist list for a specific PR campaign. Prefer Medialyst's asynchronous media-list research workflow when available, with explicit approval before credit spend; otherwise produce a best-effort local list without guessed contacts.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
ai-visibility-writing
Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite its useful information. Use when someone asks for AI visibility, AI search, answer-engine, AEO, GEO, AI Overview, or…