agentmods.dev

inject

inject is a skill for Claude Code from toss/apps-in-toss-harness. It costs 198 tokens per session (3,571 once invoked), scanned A, original, BSD-3-Clause.

A set of commands for adding development features to an existing Apps in Toss mini-app. Its separate options add browser mock tools, on-device debugging support, or the Tossface emoji font.

In plain words
What is it for?
Use it to add browser SDK mocks, connect debugging to a real device, or make emoji use the Tossface typeface across the project.
Why use it?
It avoids replacing an existing project or manually editing several build and style files. Each option handles one development or display change without automatically applying the others.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the ait plugin — 11 skills, 4 commands shipped together

not rated 186repo +10 3d ago A scan 198 tokens original BSD-3-Clause

Good fit Use it to add browser SDK mocks, connect debugging to a real device, or make emoji use the Tossface typeface across the project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/toss/apps-in-toss-harness/inject
View source ↗ toss/apps-in-toss-harness
Install

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.

Any agent
npx skills add toss/apps-in-toss-harness --skill inject
Clone the repo
git clone --depth 1 https://github.com/toss/apps-in-toss-harness

Made for: Claude Code.

Or install ait, the plugin that ships this one along with the rest of its 11 skills, 4 commands.

Wrote 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.

agentmods badge for inject

README.md
[![agentmods](https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/inject/github.svg)](https://agentmods.dev/skills/toss/apps-in-toss-harness/inject)
Your own site
<a href="https://agentmods.dev/skills/toss/apps-in-toss-harness/inject"><img src="https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/inject/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.

agentmods 80×15 button for inject

Your own site · 80×15
<a href="https://agentmods.dev/skills/toss/apps-in-toss-harness/inject"><img src="https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/inject.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 198 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,571 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00198 $0.03571
Opus 5.5 $0.00079 $0.01428
Sonnet 5.5 $0.00040 $0.00714
Haiku 4.5 $0.00020 $0.00357

Measured 6d ago against content hash dab9035c304b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

inject 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 6d 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.

packages/agent-plugin/shared/skills/inject/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

inject skill

이 skill은 세 facet을 담는다 — /ait:inject-devtools(devtools unplugin 주입), /ait:inject-debug-console(on-device attach 패키지 설치), /ait:inject-tossface(이모지 서체 Tossface 배선). 셋 다 기존 프로젝트의 빌드 셋업을 최소 변경으로 패치하는 brownfield station 2 도구라 하나로 묶였다(agent-plugin#280 debug-console facet 추가). 사용자가 어느 command로 진입했는지에 따라 아래 해당 facet으로 분기한다 — 세 facet은 독립이며 서로를 자동 실행하지 않는다.

목적

이미 @apps-in-toss/web-framework를 쓰는 기존 미니앱 프로젝트의 개발 환경을 확장한다. new-miniapp이 greenfield(빈 디렉토리)라면 이 skill은 brownfield — 기존 파일을 최소한으로 수정하고, 이미 설정이 있으면 skip한다. 어느 facet이든 생성·수정하는 파일에 과장·홍보성 문구를 넣지 않는다.

세 facet은 목적이 다르다:

  • devtools facet (/ait:inject-devtools): @apps-in-toss/devtools unplugin을 빌드 config에 추가해 토스 앱 없이 브라우저에서 mock SDK로 개발·테스트한다. 인자 없음.
  • debug-console facet (/ait:inject-debug-console): @apps-in-toss/debug-console(on-device attach)을 **dependencies**로 설치하고 /auto self-gating import를 진입점에 와이어업한다. 환경 3(intoss-private candidate) on-device 디버깅에 attach 표면을 남긴다. 인자 없음.
  • tossface facet (/ait:inject-tossface): 이모지를 토스페이스 글리프로 렌더하도록 CDN 링크 또는 서체 subset 번들을 프로젝트 전역 스타일시트에 와이어업한다. design skill의 서체 정책상 본문 서체는 금지 대상이지만 이모지 서체(Tossface)는 권장 대상이다. 인자 없음.

devtools facet — /ait:inject-devtools

번들러는 스택을 가정하지 않고 프로젝트의 package.json scripts와 번들러 설정 파일에서 읽는다. lockfile로 패키지 매니저를 감지해 @apps-in-toss/devtools를 devDep으로 설치한 뒤, 설치된 패키지 README(node_modules/@apps-in-toss/devtools/README.md)에서 그 번들러의 배선 절을 찾아 그대로 등록한다. 번들러별 코드는 이 skill이 들고 있지 않다. README가 다루지 않는 번들러면 사용자에게 알리고 묻는다. 이미 설정이 있으면 skip. 콘솔 인증 불필요 — 로컬 dev 전용이고, production 번들에는 넣지 않는다.

핵심 절차: (1) package.json 확인 → (2) 번들러 확인 → (3) PM 감지 → (4) idempotency 확인 → (5) devDep 설치 → (6) README의 해당 번들러 절대로 최소 변경 등록 → (6-1) dev 서버·빌드로 사후 검증 → (7) 완료 seam. README 읽는 법·지원 범위 밖 처리·유지할 앱인토스 고유 사실·하지 말아야 할 것은 —

상세가 필요하면 Read <이 skill의 base directory>/references/devtools.md.

debug-console facet — /ait:inject-debug-console

@apps-in-toss/debug-console을 runtime dependency로 설치하고(harness GitHub Release tarball URL — npm 미발행), 진입점에 self-gating import '@apps-in-toss/debug-console/auto'를 멱등하게 삽입한다. 이 패키지는 예전 @apps-in-toss/devtools의 ./in-app export였다 — devtools의 MCP 데몬·on-device attach 표면이 debugger 패키지(@apps-in-toss/debugger + @apps-in-toss/debug-console)로 분리되면서 나뉘었다. 보안 스코프: 두 패키지 중 프로덕션 미니앱 번들에 실제로 들어갈 수 있는 유일한 패키지라 dependencies로 설치한다(devtools는 devDep 전용) — 설치돼 있지 않으면 attach 코드가 번들에 구조적으로 들어갈 수 없다. 패키지 README는 프로덕션 하드닝 관점에서 build-time __DEBUG_BUILD__ 게이트(방식 B)를 권장 순서상 먼저 제시하지만, 이 skill이 진입점에 실제로 자동 삽입하는 것은 여전히 /auto(방식 A)다 — consumer 번들러 define 배선이 프로젝트마다 달라 이 skill이 방식 B를 강제 적용하면 기존 빌드 설정과 충돌할 수 있기 때문이다. 방식 B는 사용자가 원할 때 참고할 대안으로 references/debug-console.md에 안내한다.

Read the full file on GitHub · 183 lines

Files

What ships with it

3 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.

Changes

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.

  1. 6d ago First seen · 183 lines · 198 tokens per session scan A dab9035c304b

Subscribe to this mod's changes

inject is a skill published in the GitHub repository toss/apps-in-toss-harness (186 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 198 tokens to every session and 3,571 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-10-23.

DebuggingDesign and UX
Related

Other skills, from other repositories

html-ppt-zhangzara-block-frame

Rescuing a messy startup deck into a board-grade system — the diagnosis, the page grammar, and the rebuilt proof pages. Built as a decision-grade design craft deck for founders, exec presenter.

nexu-io/open-design · 51 tokens

accesslint-scan

Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.

sickn33/agentic-awesome-skills · 32 tokens

check

Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.

tw93/Waza · 41 tokens

health

Audits agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks wrong. Not for application bugs or PR review.

tw93/Waza · 40 tokens

hunt

Finds root cause before any fix. Use when something errors, crashes, regresses, or used to work. Not for code review or new features.

tw93/Waza · 33 tokens

think

Turns rough ideas into approved, decision-complete plans before coding. Use when planning architecture, judging whether to build, or writing a handoff. Not for bug fixes or small edits.

tw93/Waza · 39 tokens