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 xD4O/praxis --skill using-praxisgit clone --depth 1 https://github.com/xD4O/praxisWrote 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/xd4o/praxis/using-praxis)<a href="https://agentmods.dev/skills/xd4o/praxis/using-praxis"><img src="https://agentmods.dev/badge/skills/xd4o/praxis/using-praxis/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/xd4o/praxis/using-praxis"><img src="https://agentmods.dev/badge/skills/xd4o/praxis/using-praxis.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 | $0.00095 | $0.01431 |
| Opus 5.5 | $0.00038 | $0.00572 |
| Sonnet 5.5 | $0.00019 | $0.00286 |
| Haiku 4.5 | $0.00010 | $0.00143 |
Grade A, and why
using-praxis 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 15d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRAXIS Router
PRAXIS does two things before any code or plan is produced:
- Converge — make sure you and the user mean the same thing (
intent-alignment). - Reason — apply the right framework for the problem type, then validate the result.
Complexity gate
Trivial — respond directly, no protocol: typo fixes, renames, one-liners, factual questions, running commands, formatting, syntax explanations, simple file edits, git operations, package installs.
Everything else routes below. If unsure, run the QUICK tier — it costs under a minute. And if you catch yourself thinking "I can handle this directly" or "this is straightforward enough" on a task that matches a routing row, treat that impulse as the signal to route, not to skip.
Depth tiers
Scale rigor to irreversibility × blast radius:
- QUICK — run the protocol's gates mentally; report a 3–5 line summary. For small, reversible work, or when the user asks for brevity.
- STANDARD — the full protocol as written. Default for non-trivial work.
- DEEP — full protocol plus fresh-context review (see gap-analysis). Required for Type 1 hard-to-reverse decisions: schemas, public API contracts, core data models, infrastructure choices.
Routing
Identify every row that applies — protocols compose, they don't compete:
| The task involves | Protocol |
|---|---|
| A request whose scope or goal could be read more than one way | intent-alignment — always first |
| Starting any new design or feature | problem-classification |
| Turning a vague or open-ended request into a defined build scope | scoping |
| Turning a settled goal into a sequenced plan or milestones | project-planning |
| Architecture, module boundaries, build-vs-buy | architecture-reasoning |
| Designing a data model, schema, or core entities and relationships | domain-modeling |
| Auth, authorization, crypto, input handling, PII, payments | security-reasoning |
| Choosing between options, trade-offs, priorities | decision-analysis |
| Debugging, investigating, diagnosing failures | diagnostic-reasoning |
| Making working code faster, cheaper, or smaller | performance-reasoning |
| Deciding what to test and how; verifying a bug fix is real | testing-strategy |
| Committing to an effort, time, or cost estimate | estimation |
| Writing, reviewing, or refactoring significant code | code-quality-analysis |
| Changing code you did not write or do not yet understand | codebase-comprehension |
| Writing or revising a reusable prompt, system prompt, or agent instruction | prompt-design |
| Business strategy, positioning, roadmap priorities | strategic-reasoning |
| Creating or rewriting an agent skill (SKILL.md) | skill-authoring |
| Any design, plan, or recommendation about to be final | gap-analysis — always last |
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.
- 15d ago First seen · 125 lines · 95 tokens per session scan A bba56881ef01
using-praxis is a skill published in the GitHub repository xD4O/praxis (28 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 1,431 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 2026-10-02.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.