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-prompt-engine/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-prompt-engine)<a href="https://agentmods.dev/skills/symphos-ai/orcho-core/orcho-prompt-engine"><img src="https://agentmods.dev/badge/skills/symphos-ai/orcho-core/orcho-prompt-engine/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-prompt-engine"><img src="https://agentmods.dev/badge/skills/symphos-ai/orcho-core/orcho-prompt-engine.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 | $0.00077 | $0.00482 |
| Opus 5.5 | $0.00031 | $0.00193 |
| Sonnet 5.5 | $0.00015 | $0.00096 |
| Haiku 4.5 | $0.00008 | $0.00048 |
Grade A, and why
orcho-prompt-engine 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 2mo 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 Prompt Engine
Work safely on prompt composition, prompt contracts, cache layout, and prompt evidence. Keep machine contracts in code-owned prompt blocks, not loose prose.
First Reads
orcho-core/AGENTS.mdorcho-core/pipeline/prompts/AGENTS.mdorcho-core/core/_prompts/AGENTS.mdorcho-core/docs/adr/0009-composable-prompt-parts.mdorcho-core/docs/adr/0028-cache-first-physical-wire-layout.md- changed prompt builder/template files
Owns
pipeline/prompts/*core/_prompts/*- prompt part ordering and cache metadata
- prompt contract templates and protected system-tail policy
- prompt render evidence and prompt snapshots
Does Not Own
- runtime adapter invocation ->
orcho-core-runtime-session - SDK/MCP public payload shape ->
orcho-core-sdk-wire - parser/gate verdict semantics ->
orcho-core-quality-gates
Invariants
- Think in ordered prompt parts, not one rendered string.
- Preserve cache-stable prefix ordering unless deliberately changing it with tests.
- Put dynamic facts in typed prompt parts with explicit stability/cache scope.
- Keep protected contracts in code-owned templates.
- Do not silently widen editable markdown into protocol policy.
Verification
- From
orcho-core:python -m pytest -q tests/unit/pipeline/prompts - From
orcho-core:python -m pytest -q tests/unit/pipeline/runtime/test_snapshot_session_parity.pywhen cache/session behavior changes - Review prompt snapshot/golden diffs before accepting them.
Neighbor Skills
orcho-core-runtime-sessionwhen prompt/session continuity changesorcho-core-evidence-observabilitywhen rendered prompt data is persisted as evidenceorcho-labwhen evaluating prompt variants
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.
- 2mo ago First seen · 53 lines · 77 tokens per session scan A dc2074599d59
orcho-prompt-engine is a skill published in the GitHub repository symphos-ai/orcho-core (5 stars, last pushed 17d ago), licensed Apache-2.0. It adds 77 tokens to every session and 482 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
model-sovereignty
This skill should be used when the user asks about "local models", "custom models", "fine-tuning", "self-hosting models", "model selection", "which model should I use", "data privacy and models", "LoRA", "RAG vs fine-tuning", "Ollama", "vLLM", or wants guidance on whether to build, host, or customise their own AI…
v4-best-practices
Use when working with deepseek-v4-pro or deepseek-v4-flash in thinking mode on multi-step or plan-driven tasks. Provides rules to prevent stale references, unverified plan assumptions, and vague plan output.
kermt-pretrain-scratch
Pretrain a fresh KERMT model from scratch on a user-provided corpus. Builds a new vocabulary from the corpus, instantiates the model architecture from defaults, and launches pretrainddp.py inside the kermt container (detached for long runs). Unlike kermt-continue-pretrain, no starting checkpoint is loaded — the model…
cdf-auto-labeling
Use when a user needs to get started with CDF Auto-Labeling, plan a scenario, run or debug a shipped cookbook, author prompts or cookbooks, migrate a pipeline, configure a stage, or pull the prebuilt stage containers from NGC (nvcr.io). Confirm critical inputs (data path, output path, endpoints) and ask when any are…
discount-review
Inspect the discount policy fixture with a repeatable review checklist and helper script.
code-review
Reviews code for bugs, security issues, and best practices.