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 agents/fabkho/the-i18n-kit/docs-stylegit clone --depth 1 https://github.com/fabkho/the-i18n-kitWrote 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/agents/fabkho/the-i18n-kit/docs-style)<a href="https://agentmods.dev/agents/fabkho/the-i18n-kit/docs-style"><img src="https://agentmods.dev/badge/agents/fabkho/the-i18n-kit/docs-style.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 | $0.00000 | $0.02387 |
| Opus 5 | $0.00000 | $0.01193 |
| Sonnet 5 | $0.00000 | $0.00477 |
| Haiku 4.5 | $0.00000 | $0.00239 |
Grade A, and why
docs-style 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 4d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing docs for the-i18n-kit
Canonical house style for the documentation site. The
i18n-kit-docsskill under.claude/skills/points here —.claude/is gitignored, so it cannot be shared with contributors or CI.
House style, derived from the Nuxt documentation style guide and adapted to this project's positioning. Follow it exactly — the site's value depends on forty pages reading as though one person wrote them.
Who you are writing for
Two audiences, in this order:
- Someone whose AI agent will use this. They care whether the tool respects a context window and whether its output is machine-readable. They skim.
- Someone maintaining i18n in a large monorepo. They care about layers, shared libraries and not deleting a key that turns out to be in use. They read closely and distrust confident claims.
A third group — small single-locale projects — is welcome but not the target. Never pretend otherwise. Honesty about fit buys credibility for everything else.
Voice
- Second person. "You configure", not "the user configures" or "we configure".
- Active voice. "The scanner reports the key", not "the key is reported".
- Present tense for behaviour. "The CLI exits non-zero", not "will exit".
- Friendly and direct. Personality is fine; clarity wins any conflict.
- Assume competence and diverse backgrounds. Never talk down.
Banned
- "Simply", "just", "obviously", "of course", "easy". They tell a stuck reader the fault is theirs. Delete the word; the sentence is usually already correct. Not "simply make sure the config returns an object" — "make sure the config returns an object".
- Marketing adjectives with nothing behind them — "powerful", "seamless", "blazing fast", "revolutionary". State the mechanism instead. Not "powerful orphan detection" but "reports which apps consume a layer before calling a key unused".
- "Wrapper" for the MCP server in reader-facing prose. It is accurate internally and undersells externally. On the architecture page, say the MCP server depends on the CLI package and explain what that buys the reader: identical results from terminal and agent.
- Emoji in body prose. Callout components carry their own icons.
- Future-tense roadmap talk inside reference pages. If it does not ship, it does not belong outside the roadmap page.
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.
- 4d ago First seen · 238 lines · 0 tokens per session scan A 1b9d686c2353
docs-style is an agent published in the GitHub repository fabkho/the-i18n-kit (11 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,387 tokens. 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 agents, from other repositories
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
td-surveyor
You scout one surface of tdmcp (an MCP server for TouchDesigner: Node/TS server + Python TD bridge + a local-LLM copilot) and return every credible new feature that surface could gain. You are one of up to five surveyors running in parallel; stay strictly inside your assigned surface so the scopes don't collide.…
project-manager
Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.
context
Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.