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 commands/lingodotdev/lingo.dev/analyze-bucket-typegit clone --depth 1 https://github.com/lingodotdev/lingo.devWhat 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 | $0.00011 | $0.00627 |
| Opus 5 | $0.00005 | $0.00313 |
| Sonnet 5 | $0.00002 | $0.00125 |
| Haiku 4.5 | $0.00001 | $0.00063 |
Grade A, and why
analyze-bucket-type scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Given the bucket type ID "$ARGUMENTS" (e.g., "json", "mdx", "typescript"), analyze the implementation code to identify ALL bucket-specific behaviors, configurations, and characteristics.
Instructions
-
Locate where this bucket type is processed in the codebase by searching for the bucket type string. Start with the main loader composition/pipeline code.
-
Trace the complete execution pipeline for this bucket:
- List every function/loader in the processing chain, in order
- For each function/loader, read its implementation to understand:
- Input parameters it receives
- Transformations it performs on the data
- Output format it produces
- Any side effects or file operations
-
Identify configuration parameters by:
- Finding which variables are passed into the loaders (e.g., lockedKeys, ignoredKeys)
- Tracing these variables back to their source (configuration parsing)
- Determining if they're bucket-specific or universal
-
Analyze file I/O behavior:
- How are file paths constructed?
- Does the path pattern contain locale placeholders that would create separate files?
- What file operations are performed (read, write, create, delete)?
- Are files overwritten or are new files created?
- IMPORTANT: Note that "overwrites existing files completely" and "[locale] placeholder support" are mutually exclusive in practice:
- If a bucket type stores all locales in a single file (like CSV with columns per locale), it overwrites that single file and does NOT support
[locale]placeholders - If a bucket type creates separate files per locale using
[locale]placeholders, each locale file is overwritten individually - Clarify which pattern the bucket type follows
- If a bucket type stores all locales in a single file (like CSV with columns per locale), it overwrites that single file and does NOT support
-
Examine data transformation logic:
- How is the file content parsed?
- What internal data structures are used?
- How is the data serialized back to file format?
- Are there any format-preserving mechanisms?
-
Identify special behaviors by examining:
- Conditional logic specific to this bucket
- Error handling unique to this format
- Any validation or normalization steps
- Interactions between multiple loaders in the pipeline
-
Determine constraints and capabilities:
- What data types/structures are supported?
- Are there any size or complexity limitations?
- What happens with edge cases (empty files, malformed content)?
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.
- 2d ago First seen · 75 lines · 11 tokens per session scan A 0d63785b25eb
analyze-bucket-type is a command published in the GitHub repository lingodotdev/lingo.dev (5,404 stars, last pushed 2d ago), licensed Apache-2.0. It adds 11 tokens to every session and 627 once invoked, about $0.0001 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 commands, from other repositories
sonicjs-seo-blog
Generate a high-quality, SEO-optimized blog post for SonicJS on the topic: $ARGUMENTS.
sonicjs-seo-audit
Perform a comprehensive SEO audit of the SonicJS documentation website (www/).
upgrade-webkit
Upgrade Bun's WebKit fork to the latest upstream version of WebKit.
compound
현재 작업에서 재사용 패턴을 추출해 AGENTS.md·문서를 업데이트한다. 같은 종류의 버그·구현을 2회 이상 해결했거나 작업 종료 시 재사용 가치가 보일 때 사용. 일회성 작업에는 쓰지 않는다.
dedupe
Find duplicate GitHub issues.
audit
Command "audit" from chohra-med/expo_boilerplate, covering invocation, checks and output.