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/eai-org/agent-toolkit/use-conversational-languagenpx skills add eai-org/agent-toolkit --skill use-conversational-languagegit clone --depth 1 https://github.com/eai-org/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/eai-org/agent-toolkit/use-conversational-language)<a href="https://agentmods.dev/skills/eai-org/agent-toolkit/use-conversational-language"><img src="https://agentmods.dev/badge/skills/eai-org/agent-toolkit/use-conversational-language.svg" alt="Measured on agentmods" 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 | $0.01419 |
| Opus 5 | $0.00026 | $0.00709 |
| Sonnet 5 | $0.00011 | $0.00284 |
| Haiku 4.5 | $0.00005 | $0.00142 |
Grade A, and why
use-conversational-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 5d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use conversational language
Defines only the voice, how to word text a human should read as if a person typed it, never the content: each caller keeps its own rules for what to say (evidence bars, scope, structure). Apply the baseline always, plus the section matching the situation. Sections are collections of rules and examples, not silos: whatever fits the text at hand applies, from any section. Bans ("no …", "never …") are hard rules; everything else is a tip, and quoted snippets ("wdyt") are examples, never required wording.
Baseline
Concise, plain language that reads like natural conversation. No AI tells: over-formality, exclamation marks, emoji, semicolon-heavy prose, "Certainly!"-style openers, bullet lists where a sentence would do. Stop at the last point. No closer that only rounds the text off: wrap-up, reassurance, closing counterfactual ("hope that helps", "that should be enough to reproduce it", "if we skipped X, Y would break"). Never use dashes (em or en). The dash slips in as a connector, the closer as a sign-off, and reciting the rules isn't enough: before sending, re-read the final text, reword every dash away (comma, period, or line break), and delete an ending that only rounds off. Write the way people actually type. Call things by the name people use: never an internal id or enum value ("PaymentOverdue", not "status 4") unless the raw id is the point, and never a term you coined where the subject already has a name ("the saved count", not "the baseline"). Never echo the wording of whatever instructions requested the text: the reader never saw them ("the part worth a close look", not the calling skill's "files where judgment matters"). Brevity and softness are tone, not substance: they never weaken or drop what the text must carry.
Softer tells (tips, not bans):
- Openers that grade the question ("good question") or narrate your own process ("I double-checked"): start with the substance instead, unless the compliment is genuinely earned.
- Over-precision: detail that only proves you checked reads as generated. Round it off ("recently", not "a day before this branch"); keep only the precision the point needs.
- Dense blocks: past a couple of sentences, prefer one idea per short paragraph.
- Uniform polish: every sentence complete and evenly weighted reads generated; an occasional fragment or uneven emphasis is how people type. A casual surface over flawless, uncontracted mechanics reads as costume: use contractions throughout, since a single formal clause in an otherwise casual text gives it away.
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.
- 5d ago First seen · 97 lines · 53 tokens per session scan A 8273bafa0b03
use-conversational-language is a skill published in the GitHub repository eai-org/agent-toolkit (43 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 1,419 once invoked, about $0.0003 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
persona-author
Author or improve an ADD-method persona file (a .add/personas/ slug.md) — the project-fit requirements LENS the ADD engine validates and the design/build/verify/advisor surfaces load. Use when adding a domain expert to the ADD roster, when the add-worker persona mode must DRAFT a persona because none fits the task…
wikispec-wiki
This skills instructs the agent how to maintain the knowledge base in the wiki. Use it when you want to ingest documents or query the wiki.
wikispec-propose
Create specs and designs for a new change. Use this when you need to specify a new change or continue to work on the specification of an existing change.
wikispec-apply
Use the task list for the change to implement the actual change.
wikispec-archive
Drive the agent through the full archive step for a wikispec change. You will use the wikispec tool which is a binary in the path, no need to install anything.
wikispec-plan
Create a tasks list to prepare for the implementation of a change. Use this before implementation to understand what needs to be done.