orcho-core: Skill for Claude Code

.agents/skills/orcho-core-sdk-wire/SKILL.md

orcho-core-sdk-wire is a skill for Claude Code, Codex from symphos-ai/orcho-core. It costs 77 tokens per session (457 once invoked), scanned A, original, Apache-2.0.

A set of rules for changing the public Python SDK and the data formats exposed through MCP, a standard way for AI tools to connect to applications.

In plain words
What is it for?
It helps edit public data classes and run, status, history, evidence, metrics, cost, plan, review, release, and run-difference payloads, along with their tests and schema checks.
Why use it?
It helps prevent incompatible changes to shared data structures and keeps the SDK, schemas, and MCP integration aligned.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is symphos-ai/orcho-core's own configuration. It tells Claude Code and Codex how to work on orcho-core itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything orcho-core configures →

Reuse

Borrowing it

Nothing to install: this file belongs to symphos-ai/orcho-core. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/symphos-ai/orcho-core/main/.agents/skills/orcho-core-sdk-wire/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/symphos-ai/orcho-core

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for orcho-core-sdk-wire

README.md
[![agentmods](https://agentmods.dev/badge/skills/symphos-ai/orcho-core/orcho-core-sdk-wire/github.svg)](https://agentmods.dev/skills/symphos-ai/orcho-core/orcho-core-sdk-wire)
Your own site
<a href="https://agentmods.dev/skills/symphos-ai/orcho-core/orcho-core-sdk-wire"><img src="https://agentmods.dev/badge/skills/symphos-ai/orcho-core/orcho-core-sdk-wire/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.

agentmods 80×15 button for orcho-core-sdk-wire

Your own site · 80×15
<a href="https://agentmods.dev/skills/symphos-ai/orcho-core/orcho-core-sdk-wire"><img src="https://agentmods.dev/badge/skills/symphos-ai/orcho-core/orcho-core-sdk-wire.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 457 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.00457
Opus 5 $0.00039 $0.00229
Sonnet 5 $0.00015 $0.00091
Haiku 4.5 $0.00008 $0.00046

Measured 11d ago against content hash ff1a73722346, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

orcho-core-sdk-wire 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 11d 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.

.agents/skills/orcho-core-sdk-wire/SKILL.md · 52 lines

What it actually says

Orcho Core SDK Wire

Protect the public Python SDK and MCP-visible core payload shape.

First Reads

  • orcho-core/AGENTS.md
  • orcho-core/sdk/types.py
  • changed orcho-core/sdk/* file
  • orcho-core/docs/sdk_schema.json when schema changes
  • orcho-core/docs/adr/0021-public-sdk-boundary.md

Owns

  • orcho-core/sdk/*
  • SDK-visible run/status/history/evidence/metrics/cost/run-diff payloads
  • docs/sdk_schema.json
  • public plan/review/release wire shape
  • core-side shape that orcho-mcp adapts

Does Not Own

  • parser implementation details -> orcho-core-quality-gates
  • evidence internals -> orcho-core-evidence-observability
  • prompt prose -> orcho-prompt-engine
  • MCP handler implementation -> orcho-mcp

Invariants

  • Public SDK returns typed dataclasses, not ad-hoc dicts.
  • No print, sys.exit, or environment mutation in SDK APIs.
  • Schema changes require snapshot updates and MCP alignment.
  • Wire-format changes need same-change orcho-mcp validation.

Verification

  • python -m pytest -q orcho-core/tests/sdk/test_schema_snapshot.py
  • relevant orcho-core/tests/sdk/test_*
  • matching orcho-mcp schema/registration/E2E smoke for exposed changes

Neighbor Skills

  • orcho-mcp for MCP-visible changes
  • orcho-core-evidence-observability for evidence/status slices
  • orcho-core-quality-gates for parser/gate payloads
  • orcho-public-boundary for public docs/docstrings
Changes

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.

  1. 11d ago First seen · 52 lines · 77 tokens per session scan A ff1a73722346

Subscribe to this mod's changes

orcho-core-sdk-wire is a skill published in the GitHub repository symphos-ai/orcho-core (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 77 tokens to every session and 457 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.

Related

Other skills, from other repositories

review-deep

Drive the deep-review phase of an automated PR review. Consumes the walkthrough, runs the deterministic deep-review workflow (parallel lenses → adversarial validation → code-enforced threshold/caps), drafts the surviving findings, and completes the review run.

ShreyPaharia/octomux · 52 tokens

review-orchestrator

Drive an automated PR review. Produces a structured walkthrough plus inline draft comments via the octomux review CLI. NEVER posts to GitHub directly — publishing is human-gated.

ShreyPaharia/octomux · 41 tokens

review-pr

Use when reviewing a pull request, posting PR review comments, or when user says /review-pr. Reviews code with parallel agents and posts a pending GitHub review with inline comments.

ShreyPaharia/octomux · 39 tokens

review-walkthrough

Drive the walkthrough phase of an automated PR review. Produces a structured walkthrough JSON only — no inline comment drafts. The deep-review agent is attached automatically by the server after this agent finishes.

ShreyPaharia/octomux · 43 tokens

create-pr

Use when creating a pull request, opening a PR, or pushing and creating a PR for an octomux task.

ShreyPaharia/octomux · 26 tokens

ship-pr

Use to ship a change end-to-end from an octomux task — write a walkthrough, gate on a code review, open the PR, then monitor CI/comments and push fixes, finally refreshing the walkthrough. Heavier than create-pr; use when you want the full review→ship→watch loop, not just opening a PR.

ShreyPaharia/octomux · 70 tokens