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 jeet129/praxis --skill agentic-harness-orchestrationgit clone --depth 1 https://github.com/jeet129/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/jeet129/praxis/agentic-harness-orchestration)<a href="https://agentmods.dev/skills/jeet129/praxis/agentic-harness-orchestration"><img src="https://agentmods.dev/badge/skills/jeet129/praxis/agentic-harness-orchestration/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/jeet129/praxis/agentic-harness-orchestration"><img src="https://agentmods.dev/badge/skills/jeet129/praxis/agentic-harness-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00073 | $0.00999 |
| Opus 5 | $0.00036 | $0.00500 |
| Sonnet 5 | $0.00015 | $0.00200 |
| Haiku 4.5 | $0.00007 | $0.00100 |
Grade A, and why
agentic-harness-orchestration 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 10d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Harness Orchestration
capability: agentic-ai
domain: cross-cutting
state: active
dependencies:
- agentic-architecture
- evaluation-engineering
- llm-safety
triggers:
- "configuring creator and reviewer harnesses"
- "swapping Claude, Codex, Gemini, Cursor, OpenCode, or custom harnesses"
- "running iterative ideation refinement"
- "checking convergence across agent feedback loops"
outputs:
- harness role binding record
- structured review packet
- revision packet
- convergence verdict
- user approval summary
consumers:
- product-manager
- solution-architect
- tech-writer
- delivery-lead
references: []
This skill keeps an agentic workflow portable across harnesses. Treat harnesses as adapters and roles as the stable contract. Claude, Codex, Gemini, Cursor, OpenCode, and future tools can be bound to roles without rewriting the workflow.
Core Principle
Do not encode product names into the reasoning protocol. Encode roles:
| Role | Responsibility |
|---|---|
| creator | produce or expand the artifact |
| reviewer | critique the artifact and produce severity-tagged findings |
| enhancer | evaluate findings, apply improvements, and explain rejected feedback |
| arbiter | decide convergence and prepare the user approval summary |
The same harness can serve multiple roles, but the run log must record that fact and each role must use a separate prompt shape.
Harness Contract
Every bound harness must be able to:
- accept a structured prompt with role, artifact, constraints, and expected output;
- return structured markdown or JSON;
- preserve artifact version labels;
- distinguish findings from rewrites;
- identify assumptions, open questions, and confidence;
- emit a verdict without claiming perfection.
If a harness cannot satisfy the contract, pause the workflow and ask the user for a replacement harness or permission to degrade to manual copy/paste handoff.
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.
- 10d ago First seen · 168 lines · 73 tokens per session scan A a37f0614883d
agentic-harness-orchestration is a skill published in the GitHub repository jeet129/praxis (7 stars, last pushed 6d ago), licensed MIT. It adds 73 tokens to every session and 999 once invoked, about $0.0004 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…