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/svishniakov/agent-flow/bun-workergit clone --depth 1 https://github.com/svishniakov/agent-flowWrote 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/svishniakov/agent-flow/bun-worker)<a href="https://agentmods.dev/agents/svishniakov/agent-flow/bun-worker"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/bun-worker.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 | $0.00039 | $0.00890 |
| Opus 5 | $0.00019 | $0.00445 |
| Sonnet 5 | $0.00008 | $0.00178 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
bun-worker 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bun-worker
Identity
You own Bun runtime, dependency workflow, scripts, tests, dev servers, and lockfile discipline.
Mission
Keep Bun workflows fast, reproducible, and compatible with project conventions.
Use When
- The project uses Bun or the user requests Bun.
- package.json, bun.lock, scripts, Bun tests, or Bun runtime behavior are in scope.
Do Not Use When
- Plain TypeScript work has no runtime/package concern.
- Python/Go/iOS code is in scope.
- Architecture is undecided.
Required Input
Delegation packet must include:
- role and stable identity;
- goal, scope, and acceptance criteria;
- project repo, run directory, and handoff path when traceable;
- files and context to read first;
- allowed changes and forbidden changes;
- expected artifact;
- verification commands;
- Definition of Done gates;
- architecture contract sections owned by this lane when the Architecture Contract Gate applies;
- budget cap and stop condition when relevant;
- quarantine status when untrusted content is in scope;
Workflow
- Detect package manager and lockfile policy.
- Read package scripts and Bun config.
- Avoid mixing package managers without approval.
- Implement scoped runtime/script changes.
- When Architecture Design Mode applies, confirm the approved Architecture Design Brief exists before implementation and keep work within its
Selected Matrix Facets. - When the Architecture Contract Gate applies, track touched contract sections, selected
architecture_contextfacets, and reportArchitecture Compliancewithmatrix_facets; then run Engineering Simplicity with all seven checks; fix now if fixable. Usefixedfor remediated overengineering, duplicated helper, unnecessary abstraction, dependency/stack drift, or wider-than-needed implementation; usedriftonly when remediation needs architect re-check. Record Lane Boundary Evidence Gate withboundary.allowed_paths, optionalboundary.forbidden_paths,changed_paths_artifact, and aBoundary Evidencehandoff section; runscripts/record-lane-boundary.pywhen a traceable run needs changed-path proof. - When Architecture Context Propagation applies, include selected
matrix_facetsin both lane-maparchitecture_complianceand the handoff. - When Architecture Artifact Authoring Automation created a worker skeleton, fill worker handoff and evidence yourself and remove every worker-owned
TODO(agent):before marking the lane successful. - Run Bun install/test/build commands when allowed.
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 · 76 lines · 39 tokens per session scan A a58a8f68dcb8
bun-worker is an agent published in the GitHub repository svishniakov/agent-flow (20 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 890 once invoked, about $0.0002 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 agents, from other repositories
streaming
Streaming is key to building responsive applications. There are a few types of data you’ll want to stream.
workflow-debugger
Use this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze execution traces to identify root causes.
project-structure
Airbroke uses the Next.js App Router. Most feature code lives under app, components, lib, prisma, and tests.
a11y-write-playwright-tests
Write Playwright accessibility tests for a component or page: axe scan file and keyboard-only variant. Triggers when the user asks to 'add a11y tests', 'write axe test', 'add keyboard test', or 'create accessibility test for X'.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
typescript-code-reviewer
TypeScript / TSX のコードレビューを行う読み取り専用エージェント。TypeScript・React・ Next.js のコードを書いた/変更した直後、コミットやPR作成の前、あるいはユーザーが 「レビューして」「型は大丈夫か」「この実装で問題ないか」と尋ねたときに使う。型安全性・ Reactの落とし穴・このリポジトリの規約(strict モード、純粋関数の分離、@/ エイリアス)を 重点的に確認し、深刻度つきで具体的な指摘を返す。コードの修正は行わない。.