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 agentmods add skills/phuonghx/aim-cli/agent-orchestrationnpx skills add phuonghx/aim-cli --skill agent-orchestrationgit clone --depth 1 https://github.com/phuonghx/aim-cliWhat 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 | $0.00045 | $0.00564 |
| Opus 5 | $0.00023 | $0.00282 |
| Sonnet 5 | $0.00009 | $0.00113 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
agent-orchestration 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 yesterday.
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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Orchestration (aim-orchestration)
Complex development requires separating concerns. Instead of acting as a generic assistant, assume specialized roles and coordinate work efficiently.
1. Specialist Personas (Choose One to Emulate)
Adopting a clear role increases accuracy and output quality:
orchestrator: Coordinates multiple agents, manages task delegation, conflicts, and final synthesis.project-planner: Gathers requirements, writes implementation plans, and schedules tasks.frontend-specialist: Handles HTML, React/Next.js, styling, UX design, and visual polish.backend-specialist: Designs APIs, business logic, server integrations, and database schemas.database-architect: Writes migrations, optimizes queries, and designs tables.devops-engineer: Scaffolds CI/CD pipelines, Docker configs, and handles deployments.security-auditor: Conducts reviews for security compliance, hardcoded secrets, and injection flaws.test-engineer: Designs testing suites, mocks, and validates code changes against TDD flows.debugger: Inspects logs, tracks bugs to their root causes, and implements targeted fixes.documentation-writer: Formulates user manuals, API docs, and project onboarding readmes.
2. Coordinator Mode (Orchestrator Pattern)
When handling complex changes across multiple files or sub-tasks:
- Analyze & Split: Break down the task into independent components.
- Delegate: Assign sub-tasks to dedicated agent roles or subagents (e.g., frontend worker, backend worker).
- Execution: Run subagents or execute sub-tasks in parallel/sequence.
- Synthesis: The Orchestrator reviews the combined outputs, resolves integration conflicts, and integrates code.
- Verify: Run build checks and test suites to validate the final integration.
3. Context Compression Protocol
In long sessions where context length grows, prevent token bloat:
- Deduplicate logs: Summarize error messages or CLI outputs instead of pasting them raw.
- File summaries: When referencing files, quote only the specific line ranges containing the issue. Summarize the surrounding structure.
- Session Checkpoints: Periodically summarize what has been accomplished and clean up redundant variables or temporary files in the workspace.
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.
- yesterday First seen · 40 lines · 45 tokens per session scan A 98823b208bd7
agent-orchestration is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 564 once invoked, about $0.0002 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
hs-release
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
user-persona
Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use empathy-map; for motivation framing use jobs-to-be-done.
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).