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 AxWise-GmbH/axwise-flow --skill axwisegit clone --depth 1 https://github.com/AxWise-GmbH/axwise-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/skills/axwise-gmbh/axwise-flow/axwise)<a href="https://agentmods.dev/skills/axwise-gmbh/axwise-flow/axwise"><img src="https://agentmods.dev/badge/skills/axwise-gmbh/axwise-flow/axwise/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/axwise-gmbh/axwise-flow/axwise"><img src="https://agentmods.dev/badge/skills/axwise-gmbh/axwise-flow/axwise.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 | $0.00093 | $0.01491 |
| Opus 5.5 | $0.00037 | $0.00596 |
| Sonnet 5.5 | $0.00019 | $0.00298 |
| Haiku 4.5 | $0.00009 | $0.00149 |
Grade A, and why
axwise 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AxWise
Use the plugin's axwise-rust MCP server. It runs the bundled Rust standalone
engine. Select its tools from the actual advertised catalog; do not call a
legacy axwise-local server or launch a replacement MCP bridge.
If tools are deferred, use the host's tool-discovery facility to load the
advertised tools. Do not use list_mcp_resources or resource templates to
discover tool functions: this plugin publishes MCP tools. The actual server ID
is axwise-rust; a normalized function namespace is not a different server ID.
AxWise owns schemas, selected evidence, saved cohorts, domain validation, review admission, rendering and accepted storage. Codex owns model choice, authentication, tool permissions and conversation. Default host mode uses the current chat model or negotiated MCP sampling, without extracting credentials or requiring another AxWise subscription.
Choose the requested deliverable
| Request | AxWise tool |
|---|---|
| Scope, uncertainties, stakeholders and question guide | prepare_discovery |
| Synthesize market documents already selected by the user or host | research_market |
| Save a generated stakeholder cohort | generate_personas |
| Explicitly requested simulated interviews | simulate_interviews |
| Follow up with a specific saved persona | chat_with_persona |
| Analyze real or generated interview turns | analyze_interviews |
| Product or software requirements document | create_prd |
| Engineering handoff from a saved PRD | create_delivery_brief |
| Submit the requested generation, repair or review stage | advance_artifact |
Use only the steps needed for the request. An end-to-end discovery request with simulations runs scope → personas → simulations → analysis → PRD. Ordinary coding, weather and unrelated chat do not need AxWise. When the user supplies real interviews, analyze them without replacing them with generated people. Market synthesis does not retrieve the web. If the user asks to use only AxWise, work with selected inputs and identify missing evidence rather than calling search or another specialist.
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.
- 8d ago First seen · 121 lines · 93 tokens per session scan A 0783bf319b52
axwise is a skill published in the GitHub repository AxWise-GmbH/axwise-flow (62 stars, last pushed 4d ago), licensed Apache-2.0. It adds 93 tokens to every session and 1,491 once invoked, about $0.0004 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 2026-10-08.
Other skills, from other repositories
chatbot
Use when a support or sales bot on a live website must behave: persona/system prompt, grounding so it cannot invent prices or policy, jailbreak and injection defense, the human handoff, launch metrics and kill switch. NOT the agent loop or RAG index under it (that is building-agents), NOT a human answering one ticket…
evaluate
Evaluate requirements, feature requests, and task intake against project DDD context. Produces a GO/DEFER/REJECT/ESCALATE recommendation with ROI scoring, scope definition, and acceptance criteria. TRIGGER: "evaluate this request", "should we build this", "assess this requirement", "triage this". NOT FOR…
learn-content
Ingest URLs, articles, or text from any source into structured knowledge cards. Stores source URL + metadata + briefing (NOT full text). On-demand retrieval from source. TRIGGER: "learn this", "save this article", "read and remember", "ingest this". NOT FOR: deep-research, summarize, persist use cases.
persist
Persist knowledge to the correct destination — routes to DDD docs (PRODUCT/TECH/IMPROVEMENT/PROJECT), MEMORY.md, Knowledge/Library/ (searchable store), or EVOLUTION.md based on content type. Unified routing for both manual saves and auto hooks. TRIGGER: "remember", "save", "persist", "沉淀", "record this", "save to…
radar-todo
Manage SwarmAI ToDos — add, list, edit, complete, and delete items that appear in the left-nav ToDo card/overlay. Each todo is a self-contained work packet: when dragged into a chat tab, the agent has all context to start executing immediately. Also proactively creates todos from detected action items and blockers.…
deep-research
Thorough multi-source research with citations, analysis, and synthesis. TRIGGER: "research", "deep dive", "investigate", "find out about". NOT FOR: github-research, consulting-report use cases.