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/lugassawan/swe-workbench/languagesgit clone --depth 1 https://github.com/lugassawan/swe-workbenchWhat 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 | $0.00462 |
| Opus 5 | $0.00000 | $0.00231 |
| Sonnet 5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
languages 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.
This is a copy
86% identical to language-skill-required — 29 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Language catalog
All swe-workbench language skills available in this plugin. Use the Skill tool to invoke any of these.
swe-workbench:language-bash— Bash idioms: strict mode, quoting, parameter expansion, arrays, pipefail, trap cleanup, idempotency, heredocs, and POSIX portability.swe-workbench:language-csharp— C#/.NET idioms: .NET 8 LTS, nullable reference types, records, pattern matching, async/await, dependency injection, options, LINQ, and performance.swe-workbench:language-dart— Dart idioms: null safety, async, Futures/Streams, widget composition, Riverpod/Bloc app architecture.swe-workbench:language-go— Go idioms: error handling, concurrency, and standard library usage.swe-workbench:language-java— Java idioms: records, sealed types, virtual threads, streams, JDK 21+ patterns.swe-workbench:language-kotlin— Kotlin idioms: null safety, coroutines, sealed interfaces, scope functions, Flow.swe-workbench:language-python— Python idioms: PEP 8, type hints, dataclasses, asyncio, generators, pytest.swe-workbench:language-ruby— Ruby idioms: Ruby 3.x pattern matching, blocks, procs, lambdas, Enumerable, Comparable, frozen string literals, error handling, and testing.swe-workbench:language-rust— Rust idioms: ownership, borrowing, lifetimes, traits, iterators, error handling.swe-workbench:language-sql— SQL idioms: query optimization, EXPLAIN plans, schema design, transactions, deadlock avoidance, window functions, CTEs, and pagination.swe-workbench:language-swift— Swift idioms: optionals, value types, actors, async/await, protocols, Result builders.swe-workbench:language-typescript— TypeScript/JavaScript idioms: strict mode, discriminated unions, async patterns, Node.
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 · 17 lines · 0 tokens per session scan A 6ea86c862f68
languages is an agent published in the GitHub repository lugassawan/swe-workbench (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 462 tokens. A static security scan graded it A with 0 findings. It is 86% identical to language-skill-required, differing in 29 lines, and is treated as a copy.
Other agents, from other repositories
ux-ergonome
User experience and cognitive ergonomics specialist.
software-architect
Use this agent when you need expert architectural guidance, including: designing system architectures, reviewing architectural decisions, analyzing trade-offs between different architectural approaches, planning technology migrations, evaluating scalability and performance implications, assessing technical debt, or…
skill-tuning-reader
Internal read-only agent for the skill-tuning-loop workflow (and any similar mine/reflect/propose/validate pipeline). Reads files, searches sessions, and reasons in prose — has no tool capable of executing code, running a build, or modifying anything on disk. Not for direct human invocation; referenced only via a…
codegen-sync-checker
Use proactively after changes to generated-code inputs. Checks whether generated outputs are in sync without mutating the caller's working tree.
architecture-reviewer
Use proactively after larger refactors, new modules, or changes that introduce cross-package imports, exports, parts, or dependencies. Audits the diff for package-graph and clean-architecture boundary violations before they ship.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.