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 agentmods add skills/stefan-jansen/claude-code-toolkit/plain-languagenpx skills add stefan-jansen/claude-code-toolkit --skill plain-languagegit clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkitWhat 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 | $0.00039 | $0.01709 |
| Opus 5 | $0.00019 | $0.00855 |
| Sonnet 5 | $0.00008 | $0.00342 |
| Haiku 4.5 | $0.00004 | $0.00171 |
Grade A, and why
plain-language 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 3d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plain Language
Purpose: Write clearly and directly using active voice, simple sentences, and minimal jargon.
Origin: Plain Writing Act of 2010 (US), Plain Language Movement
Use When: Drafting and reviewing content to maximize clarity (Phases 4-5)
Core Principle
Plain language means readers understand immediately what you're saying - no rereading required.
Why It Matters
- Comprehension: 80% of readers prefer plain language (Bailey 2017)
- Efficiency: Plain language reduces reading time by 25-40% (Redish 1985)
- Accessibility: Technical audiences still prefer clarity over jargon
The Four Rules
1. Use Active Voice (>80% target)
Passive: Subject receives action ("The error was caught by the test") Active: Subject performs action ("The test caught the error")
Why Active is Better:
- Shorter (fewer words)
- Clearer (who does what)
- More direct (action-oriented)
Examples:
❌ PASSIVE:
"The bug was discovered by the QA team"
"Performance improvements were made to the API"
"A decision will be made by the committee"
✅ ACTIVE:
"The QA team discovered the bug"
"We improved API performance"
"The committee will decide"
Detection Pattern: "was/were/is/are + past participle + by"
When Passive is Okay:
- Unknown actor: "The system was compromised"
- Actor irrelevant: "Errors are logged automatically"
- Emphasizing recipient: "The president was elected by landslide"
2. Shorten Sentences (<25 words average)
Principle: Long sentences increase cognitive load and reduce comprehension.
Targets:
- Average: <25 words per sentence
- Maximum: Avoid >35 word sentences
- Variety: Mix short (10-15) and medium (20-25) sentences
Techniques:
❌ LONG (42 words):
"After extensive research and consideration of multiple
frameworks over several months using various criteria
including performance, ecosystem size, learning curve,
and community support, we determined that React offers
the best balance for our team's needs."
✅ SPLIT (2 sentences, 23 + 14 words):
"Our evaluation of 5 frameworks over 3 months ranked
React highest across 12 criteria, including performance,
ecosystem, and learning curve. React offers the best
balance for our team's needs."
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.
- 3d ago First seen · 244 lines · 39 tokens per session scan A f1f74f3f5608
plain-language is a skill published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,709 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
implementation-strategy
Choose compatibility-aware scope for runtime and API changes in openai-agents-python. Use before initial implementation and each review-feedback batch to decide whether to patch, reset the design, preserve compatibility, or reject unsupported cases.
examples-run-analysis
Analyze artifacts from the latest completed manual examples Make run. Read the main log, every relevant per-example log, and example source; validate every exit-0 example and classify failures, skips, and environment restrictions. Never execute or control examples.
implementation-final-review
Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…
implementation-kickoff
Start and carry an explicitly invoked openai-agents-python implementation through a fresh isolated worktree and a local PR-ready handoff. Fetch the latest origin/main, keep task changes uncommitted, replay them onto the latest main before final review, run applicable verification and $implementation-final-review, use…
test-coverage-improver
Improve test coverage in the OpenAI Agents Python repository: run make coverage, inspect coverage artifacts, identify low-coverage files, propose high-impact tests, and confirm with the user before writing tests.
openai-knowledge
Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available…