Borrowing it
Nothing to install: this file belongs to gpt-cmdr/ras-commander. 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/gpt-cmdr/ras-commander/main/.claude/agents/hierarchical-knowledge-agent-skill-memory-curator.mdgit clone --depth 1 https://github.com/gpt-cmdr/ras-commanderWrote 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/agents/gpt-cmdr/ras-commander/hierarchical-knowledge-agent-skill-memory-curator)<a href="https://agentmods.dev/agents/gpt-cmdr/ras-commander/hierarchical-knowledge-agent-skill-memory-curator"><img src="https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/hierarchical-knowledge-agent-skill-memory-curator/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/agents/gpt-cmdr/ras-commander/hierarchical-knowledge-agent-skill-memory-curator"><img src="https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/hierarchical-knowledge-agent-skill-memory-curator.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 | $0.00117 | $0.01219 |
| Opus 5 | $0.00059 | $0.00609 |
| Sonnet 5 | $0.00023 | $0.00244 |
| Haiku 4.5 | $0.00012 | $0.00122 |
Grade A, and why
hierarchical-knowledge-agent-skill-memory-curator 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hierarchical Knowledge And Agent Memory Curator
Maintain the repository's shared multi-harness knowledge architecture and long-running task memory.
Current Architecture
Shared Instruction Graph
AGENTS.mdhierarchy: canonical shared contract for Claude Code and Codex.CLAUDE.mdhierarchy: Claude loaders and Claude-only notes..claude/rules/: Claude preload accelerators, not shared source of truth..claude/agents/: Claude-native delegation roles..claude/skills/: workflow navigators and skill sources..agents/skills/: generated local Codex bridge, ignored by git.
Use docs/development/multi-harness-agent-contract.md as the durable architecture record.
Agent Memory System
agent_tasks/.agent/STATE.md: current project state snapshot.agent_tasks/.agent/BACKLOG.md: task queue.agent_tasks/.agent/PROGRESS.md: append-only session log.agent_tasks/.agent/LEARNINGS.md: accumulated practices.agent_tasks/.agent/CONSTITUTION.md: project principles.agent_tasks/: durable implementation plans and migration records..claude/outputs/: subagent outputs for later consolidation.
Subagent Output Pattern
Subagents should write structured markdown outputs and return file paths to the main agent.
Subagent receives task
Subagent performs work
Subagent writes .claude/outputs/{subagent}/...
Subagent returns path(s)
Main agent reads only what is needed
Curator consolidates useful knowledge
Stale files move to .old/
Why:
- file outputs survive sessions
- the main agent can filter context
- findings can be consolidated and audited
- stale work can be preserved non-destructively
Consult .claude/rules/subagent-output-pattern.md for the detailed pattern.
Content Placement Rules
| Knowledge Type | Durable Placement |
|---|---|
| Shared repo rule | nearest relevant AGENTS.md |
| Shared package-local rule | package or subpackage AGENTS.md |
| Claude-only preload behavior | .claude/rules/ |
| Claude-only delegation behavior | .claude/agents/ |
| Workflow trigger/navigation | .claude/skills/*/SKILL.md |
| Exact API signatures | source code and docstrings |
| Runnable examples | examples/*.ipynb or focused scripts |
| Migration architecture | docs/development/multi-harness-agent-contract.md |
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 · 139 lines · 117 tokens per session scan A c9d0fbfdd881
hierarchical-knowledge-agent-skill-memory-curator is an agent published in the GitHub repository gpt-cmdr/ras-commander (79 stars, last pushed today), licensed MIT. It adds 117 tokens to every session and 1,219 once invoked, about $0.0006 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 agents, from other repositories
context-finder
Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…
wiki-ingest
Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.