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 daffy0208/ai-dev-standards --skill orchestration-plannergit clone --depth 1 https://github.com/daffy0208/ai-dev-standardsWrote 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/daffy0208/ai-dev-standards/orchestration-planner)<a href="https://agentmods.dev/skills/daffy0208/ai-dev-standards/orchestration-planner"><img src="https://agentmods.dev/badge/skills/daffy0208/ai-dev-standards/orchestration-planner/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/daffy0208/ai-dev-standards/orchestration-planner"><img src="https://agentmods.dev/badge/skills/daffy0208/ai-dev-standards/orchestration-planner.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 | $0.00026 | $0.03312 |
| Opus 5 | $0.00013 | $0.01656 |
| Sonnet 5 | $0.00005 | $0.00662 |
| Haiku 4.5 | $0.00003 | $0.00331 |
Grade A, and why
Orchestration Planner 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 9d 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 — 462 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestration Planner
Plan multi-step workflows using capability graph and Codex-powered goal decomposition
Purpose
Takes high-level goals and decomposes them into executable workflows using the capability graph. Uses Codex to understand goal semantics, find matching capabilities, validate preconditions, and generate Hierarchical Task Network (HTN) plans with alternatives and scoring.
When to Use
- Converting user goals into executable plans (e.g., "build RAG system")
- Finding optimal capability sequences for complex tasks
- Validating that project state supports a capability
- Generating alternatives when primary path is blocked
- Explaining why certain capabilities are recommended
Key Capabilities
- Goal Decomposition: Uses Codex to break goals into required effects
- Capability Matching: Finds capabilities that produce desired effects
- Precondition Validation: Checks if current project state satisfies requirements
- HTN Planning: Builds hierarchical task networks with subtasks
- Scoring & Ranking: Evaluates paths by cost, latency, risk, diversity
- Alternative Generation: Provides fallback options when primary path fails
- Decision Logging: Captures rationale for capability selection
Inputs
inputs:
goal: string # User goal (e.g., "implement RAG")
project_state: object # Current project state (files, dependencies, env vars)
capability_graph: string # Path to capability-graph.json
preferences: object # User preferences (cost_weight, risk_tolerance, etc.)
context: array # Recently used capabilities (for cooldown)
Process
Step 1: Goal Analysis with Codex
# Use Codex to understand goal and extract required effects
codex exec "
Analyze this goal and determine what effects are needed:
GOAL: ${USER_GOAL}
Examples of effects:
- creates_vector_index
- adds_auth_middleware
- configures_database
- implements_api_endpoint
- adds_tests
Task: Extract the effects needed to achieve this goal.
Output JSON:
{
\"goal\": \"original goal\",
\"required_effects\": [\"effect1\", \"effect2\"],
\"optional_effects\": [\"effect3\"],
\"domains\": [\"rag\", \"api\"],
\"reasoning\": \"explanation\"
}
" > /tmp/goal-analysis.json
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 462 lines · 26 tokens per session scan A bc4ca44f0d42
Orchestration Planner is a skill published in the GitHub repository daffy0208/ai-dev-standards (36 stars, last pushed 8mo ago), licensed MIT. It adds 26 tokens to every session and 3,312 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
ai-native-agent-skill-design
A practical method for designing AI products made of agents and skills. It takes a task situation and maps the needed task breakdown, agent roles, skills, tools, limits, and fallback behavior.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
trigger-authoring-tasks
Covers writing backend Trigger.dev tasks with @trigger.dev/sdk: defining task() and schemaTask(), the run function and its ctx, retries, waits, queues and concurrency, idempotency keys, run metadata, logging, triggering other tasks (and the Result shape), scheduled/cron tasks, and the essentials of trigger.config.ts.…