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.
curl -O https://raw.githubusercontent.com/symphos-ai/orcho-core/main/.agents/skills/orcho-core-skills-registry/SKILL.mdgit clone --depth 1 https://github.com/symphos-ai/orcho-coreWrote 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/symphos-ai/orcho-core/orcho-core-skills-registry)<a href="https://agentmods.dev/skills/symphos-ai/orcho-core/orcho-core-skills-registry"><img src="https://agentmods.dev/badge/skills/symphos-ai/orcho-core/orcho-core-skills-registry/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/symphos-ai/orcho-core/orcho-core-skills-registry"><img src="https://agentmods.dev/badge/skills/symphos-ai/orcho-core/orcho-core-skills-registry.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 | $0.00092 | $0.00558 |
| Opus 5 | $0.00046 | $0.00279 |
| Sonnet 5 | $0.00018 | $0.00112 |
| Haiku 4.5 | $0.00009 | $0.00056 |
Grade A, and why
orcho-core-skills-registry 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 12d 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
Orcho Core Skills Registry
Own Orcho's skill discovery, trust, injection, and traceability surfaces.
First Reads
orcho-core/AGENTS.mdorcho-core/pipeline/skills/types.pyorcho-core/pipeline/skills/discover.pyorcho-core/pipeline/skills/loader.pyorcho-core/pipeline/skills/inject.pyorcho-core/agents/stream_parsers/skill_registry.pydocs/plans/core/2026-05-19-skill-traceability-cli-ux.mdwhen traceability changes
Owns
SkillPackage,SkillBinding,SkillTrustPolicy- multi-source discovery and source priority
.agents/skills,.claude/skills,.forge/skillscompatibility- trust gates and include-untrusted introspection
- skill roster rendering into planning
- full
SKILL.mdinjection into subtask prompts - skill-use stream parsing and events
- skill list/trace CLI behavior when paired with
orcho-core-cli-ux
Does Not Own
- generic prompt rendering/cache ->
orcho-prompt-engine - public SDK/MCP shape ->
orcho-core-sdk-wire - MCP handler implementation ->
orcho-mcp - general CLI formatting ->
orcho-core-cli-ux
Invariants
- Skills provide instructions, not runtime/model/provider selection.
- Project and compat skills are trust-gated by default.
- Discovery must preserve deterministic priority and shadowing diagnostics.
- Full skill bodies should not leak into durable evidence by default.
- Resource bodies are loaded only on demand.
Verification
python -m pytest -q orcho-core/tests/unit/pipeline/skillspython -m pytest -q orcho-core/tests/unit/agents/test_skill_registry.py- CLI skill tests when commands change
- MCP skill-list tests when exposed through MCP
Neighbor Skills
orcho-core-cli-uxfororcho skillscommand UXorcho-core-sdk-wirewhen skill trace/list shape becomes publicorcho-mcpfor MCP skill catalogue exposure
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.
- 12d ago First seen · 58 lines · 92 tokens per session scan A 517d17c5e9d0
orcho-core-skills-registry is a skill published in the GitHub repository symphos-ai/orcho-core (5 stars, last pushed today), licensed Apache-2.0. It adds 92 tokens to every session and 558 once invoked, about $0.0005 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
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.
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.
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.
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.
create-pr
Use when creating a pull request, opening a PR, or pushing and creating a PR for an octomux task.
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.