Borrowing it
Nothing to install: this file belongs to flisk-sh/flisk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/flisk-sh/flisk/main/.claude/skills/flisk-tool-add/SKILL.mdgit clone --depth 1 https://github.com/flisk-sh/fliskWrote 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/flisk-sh/flisk/flisk-tool-add)<a href="https://agentmods.dev/skills/flisk-sh/flisk/flisk-tool-add"><img src="https://agentmods.dev/badge/skills/flisk-sh/flisk/flisk-tool-add/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/flisk-sh/flisk/flisk-tool-add"><img src="https://agentmods.dev/badge/skills/flisk-sh/flisk/flisk-tool-add.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00137 | $0.00682 |
| Opus 5.5 | $0.00055 | $0.00273 |
| Sonnet 5.5 | $0.00027 | $0.00136 |
| Haiku 4.5 | $0.00014 | $0.00068 |
Grade A, and why
flisk-tool-add 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 5d 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.
What it actually says
Flisk add
When the user names a tool, add it with flisk tool add, not by picking flisk resource flags yourself. flisk tool add runs the right flisk resource command, or says why it cannot.
Workflow
- See what exists:
flisk tool add(no tool) lists every tool and its outcome.flisk tool add --jsongives the same as data. - Add the tool:
flisk tool add <tool> [name] [--stack <stack>]. Pass a name when the default (web,api,db…) is already taken, and--stackwhen the project has more than one stack. - Read the outcome and act on it:
- adds a resource: done. Read the printed
Next:line, then start it withflisk up(see flisk-up). - built in (Docker): tell the user; change nothing.
- manual steps (Angular, Tailwind, Spring Boot, GitHub Actions, Guidewire Jutro, PolicyCenter): show the steps to the user. Carry out the open-source ones (Angular, Tailwind, Spring Boot, GitHub Actions) only if the user asks. Never fetch or fake Guidewire software: it is licensed and the user must supply it.
- rejected (exit 1: AWS, Google Cloud, Azure, Kubernetes): stop. Tell the user Flisk runs everything on their own computer and never creates cloud resources, and offer the local alternatives the command printed. Do not work around the rejection with another command, a script or a cloud CLI.
- adds a resource: done. Read the printed
- Check it:
flisk config verifyandflisk resources.
Examples
flisk tool add react
flisk tool add fastapi orders --stack shop
flisk tool add postgresql
flisk tool add rag && flisk tool add embeddings && flisk tool add llm-api # a local RAG stack
flisk tool add nextjs --dry-run
Guardrails
- One
flisk tool addper tool the user named; do not add tools they did not ask for. - Preview with
--dry-runwhen the user is unsure. - Full guide: docs/add-a-tool.md.
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.
- 5d ago First seen · 41 lines · 137 tokens per session scan A be2665aad1fc
flisk-tool-add is a skill published in the GitHub repository flisk-sh/flisk (54 stars, last pushed yesterday), licensed MIT. It adds 137 tokens to every session and 682 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 2026-11-15.
flisk-tool-add compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| flisk-tool-addflisk-sh/flisk | Skill | 54 | yesterday | MIT | A | 137 | Claude Code |
| harborav/harbor | Skill | 3.3k | 9d ago | Apache-2.0 | A | 114 | Claude Code |
| vss-deploy-video-embeddingNVIDIA-AI-Blueprints/video-search-and-summarization | Skill | 2.0k | today | Apache-2.0 | B | 115 | Claude Code, Codex |
| rag-blueprintPracticalSwan/agent-skills | Skill | 24 | 4d ago | MIT | A | 30 | Codex |
| senior-ml-engineerricneves-ai/flowgrammers-skills | Skill | 118 | 1mo ago | MIT | A | 110 | Claude Code, Codex |
| local-rag-llamaindexSeeed-Projects/Seeed-Jetson-DevelopTool | Skill | 58 | yesterday | MIT | B | 62 | Claude Code, Codex |
| jove-youtube-feed-pipelinebuild-with-dhiraj/ai-workflow-framework-portability-kit | Skill | 5 | 1mo ago | MIT | A | 167 | Claude Code, Codex |