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 skills add pantheon-org/tekhne --skill bun-developmentgit clone --depth 1 https://github.com/pantheon-org/tekhneWrote 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/pantheon-org/tekhne/bun-development)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/bun-development"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/bun-development/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pantheon-org/tekhne/bun-development"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/bun-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00084 | $0.01313 |
| Opus 5 | $0.00042 | $0.00656 |
| Sonnet 5 | $0.00017 | $0.00263 |
| Haiku 4.5 | $0.00008 | $0.00131 |
Grade A, and why
bun-development 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 8d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bun Development
Navigation hub for Bun guidance focused on production-safe implementation.
When to Apply
Use this skill when:
- You need Bun-native runtime APIs (
Bun.file,Bun.write,Bun.serve) - You are writing or debugging tests with
bun test - You are adding
bun:sqliteusage with transactions or prepared statements - You are setting dependency/workspace policy in a Bun project
- You need deterministic security guardrails for shell/SQL inputs
When Not to Use
- The project standard runtime is strictly Node.js with no Bun support
- You need framework-specific guidance not covered by Bun APIs
- The task is only package-agnostic JavaScript refactoring
Workflow
- Confirm Bun is available and lock dependency strategy.
- Choose the category (runtime, file I/O, testing, sqlite, package, security).
- Implement with copy/paste commands from Quick Commands.
- Apply anti-pattern checks before finalizing.
- If
bun installfails: checkbun.lock/bun.lockbfor merge conflicts, resolve them, and re-runbun install. - If tests fail after dependency changes: run
bun testto isolate regressions before proceeding.
- If
- Validate behavior with tests or execution checks.
- If validation fails: revert the last change, confirm the error, and address the specific failure before re-validating.
- For SQL validation (
rgfinds non-prepared statements in existing code): refactor each flagged call to usedb.prepare(...)with bound parameters before merging; do not leave raw interpolations in place. - Document decisions with links to exact references used.
Quick Commands
Verify Runtime
bun --version
Expected: a Bun version is printed.
Install Dependencies
bun install
Expected: lockfile is updated consistently (bun.lock/bun.lockb per project setup).
Run Script
bun run src/index.ts
Expected: script executes without Node.js runtime shims.
Execute Tests
bun test
Expected: failing assertions clearly identify behavior regressions.
What ships with it
34 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .audits/2026-02-21/analysis.md 8.1 KB
- .audits/2026-02-21/audit.json 140 B
- .audits/2026-02-21/remediation-plan.md 226 B
- .audits/2026-02-22/analysis.md 8.1 KB
- .audits/2026-02-22/audit.json 140 B
- .audits/2026-02-22/remediation-plan.md 226 B
- .audits/2026-02-23/analysis.md 8.1 KB
- .audits/2026-02-23/audit.json 143 B
- .audits/2026-02-23/remediation-plan.md 222 B
- .audits/2026-03-02/analysis.md 1.0 KB
- .audits/2026-03-02/audit.json 415 B
- .audits/2026-03-02/remediation-plan.md 2.0 KB
- .audits/latest 10 B
- .tessl-plugin/plugin.json 575 B
- AGENTS.md 2.7 KB
- CHANGELOG.md 736 B
- evals/scenario-01.md 3.5 KB
- evals/scenario-02.md 3.8 KB
- evals/scenario-03.md 3.0 KB
- evals/scenario-04.md 3.5 KB
- evals/scenario-05.md 3.1 KB
- references/file-glob.md 2.7 KB
- references/file-io-patterns.md 2.4 KB
- references/file-vs-node.md 3.8 KB
- references/pm-workspaces-agent-instructions.md 3.4 KB
- references/runtime-globals.md 10 KB
- references/runtime-http-server.md 3.8 KB
- references/runtime-password.md 3.6 KB
- references/runtime-shell.md 3.5 KB
- references/sqlite-basics.md 6.1 KB
- references/testing-bun-test.md 2.3 KB
- references/testing-matchers.md 4.4 KB
- references/testing-mocking.md 5.9 KB
- references/testing-snapshots.md 5.0 KB
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.
- 8d ago First seen · 177 lines · 84 tokens per session scan A 3a7e1e717d64
bun-development is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 1,313 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
dynamodb-toolbox-patterns
Provides TypeScript patterns for DynamoDB-Toolbox v2 including schema/table/entity modeling, .build() command workflow, query/scan access patterns, batch and transaction operations, and single-table design with computed keys. Use when implementing type-safe DynamoDB access layers with DynamoDB-Toolbox v2 in TypeScript…
database-orm-expert
Updated to be the unified database skill covering ORM, migrations, edge DBs, and Supabase CLI / Keahlian database terpadu untuk ORM, migrasi, edge DB, dan Supabase CLI.
upstash-search-js
Work with the @upstash/search TypeScript/JavaScript SDK, a serverless full-text and semantic search database with built-in reranking. Use when adding search to an app or site, creating a search index, upserting documents with searchable content and filterable metadata, running keyword, semantic, or hybrid search…
drizzle-orm
Expert knowledge for Drizzle ORM - the lightweight, type-safe SQL ORM for edge and serverlessUse when "drizzle, drizzle orm, drizzle-kit, drizzle schema, drizzle migration, drizzle relations, sql orm typescript, edge database, d1 database, orm, database, typescript, sql, edge, serverless, d1, postgres, mysql, sqlite"…
psl-ast-layers
How to use the PSL syntax tree layers (green tree, red tree, strongly-typed AST classes) correctly. Use for any PSL-related work: PSL interpreters (contract-psl), helpers inside the psl-parser package, the language server, formatters, or anything else that consumes parse() output from @internal/psl-parser.
ast-visitor-pattern
Use the frozen-class/visitor pattern for discriminated unions that have multiple dispatch sites. Use when creating a new set of variants (commands, IR nodes, factory calls) that will be switched over in 2+ places, or when refactoring an existing union type that has grown multiple switch sites.