Borrowing it
Nothing to install: this file belongs to JJHbrams/Project-AMBER. 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/JJHbrams/Project-AMBER/master/.github/skills/orchestrate/SKILL.mdgit clone --depth 1 https://github.com/JJHbrams/Project-AMBERWrote 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/jjhbrams/project-amber/orchestrate)<a href="https://agentmods.dev/skills/jjhbrams/project-amber/orchestrate"><img src="https://agentmods.dev/badge/skills/jjhbrams/project-amber/orchestrate/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/jjhbrams/project-amber/orchestrate"><img src="https://agentmods.dev/badge/skills/jjhbrams/project-amber/orchestrate.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 | $0.00148 | $0.00996 |
| Opus 5.5 | $0.00059 | $0.00398 |
| Sonnet 5.5 | $0.00030 | $0.00199 |
| Haiku 4.5 | $0.00015 | $0.00100 |
Grade A, and why
orchestrate 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 24d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate
The root session is the only delegation and integration point. Use the available planner,
coder, and servant roles; provider model IDs are runtime-specific and are not a reason to
change this behavioral flow.
Phase 0 — Triage and contract
First apply the routing section of session-orchestrate, including when the user explicitly
names orchestrate. If that skill has already selected this conversational delegation path,
continue here without routing back. Handle its L0 route directly; for unattended execution,
repeat-until-pass, machine evidence audit, quantitative experiments, or cross-session resume,
return to its runtime procedure instead of starting this workflow. If session-orchestrate is
unavailable, report the missing routing dependency; do not silently substitute this workflow.
This is a root-session skill procedure, not a nested SAO worker. This conversational path returns criterion-level evidence and a root-reviewed result; it does not create a persisted SAO task or claim a machine-audited SAO PASS. For a multi-step task, capture the original request as an acceptance contract before implementation. Ask the user only about a material ambiguity that cannot be safely discovered.
Each [PLAN] criterion must contain:
acceptance_criteria:
- id: AC1
criterion: <requirement>
user_visible_outcome: <what the user can observe>
intended_runtime: <runtime, or "static-only">
verification: <how it will be checked>
evidence: <expected artifact or command result>
critical: true|false
Phase 1 — Plan
Ask planner for a read-only [PLAN]. Use servant first only when focused repository facts
are needed. Resolve material open_questions before execution. The plan may use only the
existing planner, coder, and servant roles.
Phase 2 — Plan gate and scope control
Check that every original-request outcome has a criterion, intended runtime, and verification. If a proposed action would delete, reduce, substitute, or omit verification of a criterion, emit:
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.
- 24d ago Changed · +11 lines · +73 tokens per session 1a25d7029c74
- 1mo ago First seen · 91 lines · 75 tokens per session scan A e20590804cad
orchestrate is a skill published in the GitHub repository JJHbrams/Project-AMBER (2 stars, last pushed 24d ago), licensed MIT. It adds 148 tokens to every session and 996 once invoked, about $0.0006 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
penfield
Persistent memory for AI agents. Store decisions, preferences, and context that survive across sessions. Build knowledge graphs that compound over time. Hybrid search (BM25 + vector + graph) recalls what matters when you need it.
mengram-memory
Long-term memory with 3 types (facts, events, workflows). Remember user preferences, past conversations, and learned procedures across sessions. Use when recalling what the user said before, saving important info, getting user context, or tracking completed workflows.
memory-audit-discoverability
A review guide for checking whether stored memories can be found at the right time. It focuses on where memories are attached, when they are triggered, whether aliases are missing, and whether a parent has too many children.
memory-audit-pattern-extraction
A method for investigating repeated mistakes by comparing related memories and checking whether an earlier reminder failed. It looks at where the reminder was stored, when it was created, and whether it was strong enough to prevent the mistake.
memory-audit
An entry point for reviewing and maintaining an AI agent's stored memories. It describes how to remove repetition, preserve useful reasoning, and update memories when old conclusions no longer fit.
add-connector
Onboard a deus connect connector — a way to route Claude Code sessions to non-Claude models (e.g. GPT via CLIProxyAPI) alongside normal Claude access. Generic orchestrator over whichever connector is selected.