Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tellang/trifluxnpx agentmods add skills/tellang/triflux/tfx-shipWrote 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/tellang/triflux/tfx-ship)<a href="https://agentmods.dev/skills/tellang/triflux/tfx-ship"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-ship/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/tellang/triflux/tfx-ship"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 8 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 14 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 185 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 306 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 317 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 21 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 21 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00137 | $0.04295 |
| Opus 5.5 | $0.00055 | $0.01718 |
| Sonnet 5.5 | $0.00027 | $0.00859 |
| Haiku 4.5 | $0.00014 | $0.00430 |
Grade A, and why
tfx-ship 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 18d 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tfx-ship - triflux 릴리즈 자동화
ARGUMENTS 처리: ARGUMENTS 가 있으면 첫 토큰을 version bump 타입 또는 명시 버전으로 해석. 플래그는
--skip-tests,--no-publish,--dry-run지원.
하드 룰 (절대 위반 금지):
- Commit 메시지에
Co-Authored-By:trailer 금지🤖 Generated with Claude Code/AI-assisted등 AI 공저자 언급 금지--no-verify,--no-gpg-sign,--amend금지 (사용자 명시 요청 전까지)git reset --hard,git push --force,git clean -f는 사용자 명시 승인 후에만- 버전 동기화:
package.json+.claude-plugin/marketplace.json둘 다 갱신 (release:check-sync가 강제)
배포 채널
triflux 는 아래 3채널로 동시 배포. 각 채널의 버전은 반드시 동기화 상태 유지.
| # | 채널 | 명령 | 우선순위 |
|---|---|---|---|
| 1 | GitHub Releases | gh release create vX.Y.Z --notes-file <notes> |
공지 + changelog 공식 소스 |
| 2 | npm registry | CI npm-publish.yml (v* 태그 push 자동 / OIDC Trusted Publishing) |
primary distribution |
| 3 | Claude Code marketplace | .claude-plugin/marketplace.json (source: npm 참조) |
claude plugin add triflux |
- npm publish 는 로컬에서 하지 않는다 - 버전을 올린 PR 머지 후 ci 성공,
release.ymldispatch 또는v*태그 push 시npm-publish.yml이 OIDC 로 발행한다. 로컬publish.mjs --execute는 CI 불가 시 폴백 전용. - marketplace 는 자체 publish 명령이 없음. marketplace.json 의 version 만 갱신하면 git push 로 반영됨 (GitHub 호스팅).
release:check-sync가 package.json + marketplace.json + package-lock.json 3곳 version 일치를 강제한다.
전제 조건
~/.claude/scripts/tfx-route.sh불필요 (CLI 워커 호출 없음)ghCLI 인증됨 (gh auth status) -release.ymldispatch / GitHub release 에 필요. 깨졌으면 웹 UI 대체- npm 인증 불필요 - npm publish 는 CI(
npm-publish.yml)가 OIDC 로 수행 (로컬npm login필요 없음) - 릴리즈할 커밋이
origin/main에 포함되어 있을 것. 자동 경로는 ci 의 head_sha, 수동 경로는 dispatch 시점의 github.sha 를 checkout 한다.
기본 경로 - CI 릴리즈 (권장)
PR 에서 npm run release:bump -- --version X --write 로 버전을 올려 main 에 머지하면,
같은 커밋의 ci 통과 뒤 release.yml 이 자동으로 실행된다. 버전을 안 올린 머지는 릴리즈하지 않는다.
자동 경로는 해당 커밋과 첫 번째 부모의 package.json 버전을 비교한다. 버전이 같거나 이미 태그가 있으면 건너뛰고, prerelease 는 수동 dispatch 로 진행한다.
main 이 앞서 있어도 해당 커밋이 origin/main 의 조상이면 릴리즈한다. 강제 푸시로 main 에서 사라진 커밋은 건너뛰고, 최신 안정 태그 이하로 버전이 역행하면 실패한다.
resolve 잡은 동시성 제한 없이 판정하고, 실제 release 잡만 release concurrency 그룹에서 직렬 실행한다. 자동 경로만 publish.mjs --allow-ancestor 를 사용하며 수동 경로는 기존 HEAD 동등성 검사를 유지한다.
버전을 올린 커밋 두 개가 거의 동시에 들어오면 앞의 대기 릴리즈가 취소될 수 있다. 해당 커밋의 ci 를 Re-run 하거나 release.yml 을 수동 dispatch 해 복구한다.
What ships with it
1 file 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.
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.
- 18d ago Changed 1a074c5590c6
- 19d ago Changed · -21 lines 08e3e206e416
- 1mo ago Changed 0a4c4a8938a5
- 1mo ago Changed · +7 lines · +7 tokens per session fbee624395d4
- 1mo ago First seen · 350 lines · 130 tokens per session scan A f8af9e8e1320
tfx-ship is a skill published in the GitHub repository tellang/triflux (7 stars, last pushed today), licensed MIT. It adds 137 tokens to every session and 4,295 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
swarm-migrate
Cross-repo migration swarm — one coordinator + N parallel subagents (one per target repo) that apply the same transformation, open PRs, wait for CI, and report back to a shared JSON ledger. Coordinator handles topology, conflict auto-rebase, and stop-on-novel-failure. Use when bumping a shared dependency, rolling out…
pdlc-ship
A software release workflow that runs tests, updates the version and change log, creates a Git tag, and starts CI/CD, the automated build and deployment process.
automating-devops
DevOps knowledge reference covering Git workflows, testing strategies, DevSecOps, release pipeline orchestration (release.yml, multi-arch images, cosign integration), CI/CD pipelines, database management, observability, and performance optimization. Use when working with Git, CI/CD, release pipelines, ghcr image…
release
This skill should be used when the user asks to "release", "create a release", "ship it", "publish a new version", "bump version and release", "cut a release", or mentions releasing to GitHub/npm/PyPI. Orchestrates the full release pipeline from pre-flight checks through GitHub release creation.
preflight-check
This skill should be used when the user asks to "pre-flight check", "validate before commit", "validate before PR", "validate before deploy", "is this ready to ship", "check readiness", "run pre-flight", "validate project state", or wants context-aware validation across commit/PR/release/deploy boundaries.…
kmp-release
End-to-end KMP library and app release pipeline. Covers versioning strategy (gradle.properties as source of truth), Maven Central publishing via the vanniktech plugin, GPG signing, Sonatype Central Portal, changelog generation with git-cliff and Conventional Commits, GitHub Release creation, secrets management…