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 ksachdeva/zephyr-rtos-ai --skill zephyr-memorygit clone --depth 1 https://github.com/ksachdeva/zephyr-rtos-aiWrote 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/ksachdeva/zephyr-rtos-ai/zephyr-memory)<a href="https://agentmods.dev/skills/ksachdeva/zephyr-rtos-ai/zephyr-memory"><img src="https://agentmods.dev/badge/skills/ksachdeva/zephyr-rtos-ai/zephyr-memory.svg" alt="Measured on agentmods" 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 | $0.00084 | $0.00881 |
| Opus 5 | $0.00042 | $0.00441 |
| Sonnet 5 | $0.00017 | $0.00176 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
zephyr-memory 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 8d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zephyr Memory Management
Overview
Zephyr provides multiple memory management mechanisms tailored for different embedded use cases. This skill helps select the right allocator, implement memory patterns correctly, and avoid common pitfalls.
Workflow
1. Allocator Selection
Determine requirements before choosing:
- Block size variability? Fixed vs variable-size allocations
- Determinism needed? Constant-time allocation requirements
- Fragmentation tolerance? Long-running systems need fragmentation resistance
- Memory protection? Userspace isolation requirements
- ISR context? Some allocators cannot be used from ISRs
Step 1: Read references/comparison.md for the allocator decision matrix.
2. Implementation
Once the allocator is selected, implement using the appropriate guide.
Step 2: Read the appropriate reference:
- Heaps: references/heaps.md — Variable-size dynamic allocation (
k_heap,k_malloc,sys_heap). - Memory Slabs: references/slabs.md — Fixed-size block allocation with zero fragmentation.
- Memory Blocks: references/mem_blocks.md — Multi-block allocator with external bookkeeping.
- Memory Domains: references/domains.md — Memory partitions for userspace thread isolation.
- Virtual Memory: references/virtual.md — MMU-based memory mapping and demand paging.
3. API & Configuration
For complete API signatures and Kconfig options.
Step 3: Read references/api.md for:
- Complete API function signatures for all allocators.
- Relevant Kconfig options.
- Header file locations.
4. Troubleshooting
Common memory management issues:
- Fragmentation: Use slabs or mem_blocks for fixed-size allocations; prefer multiple purpose-specific heaps over one large heap.
- Stack overflow: Enable
CONFIG_HW_STACK_PROTECTION; size stacks appropriately withCONFIG_*_STACK_SIZE. - ISR allocation failures: Never block in ISRs; use
K_NO_WAITand handle allocation failures. - Memory leaks: Track allocations; use heap listeners (
CONFIG_HEAP_LISTENER) for debugging. - Userspace access violations: Verify memory partitions are correctly configured and threads are assigned to the right domains.
What ships with it
7 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.
- 8d ago First seen · 73 lines · 84 tokens per session scan A 0d94779f5e0f
zephyr-memory is a skill published in the GitHub repository ksachdeva/zephyr-rtos-ai (23 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 84 tokens to every session and 881 once invoked, about $0.0004 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
knowledge_store_skill
Skill for working with local .knowledge.yaml files via KnowledgeStore. Use this when you need to recall, search, or manage directory-local memories and knowledge links stored in plain YAML alongside the user's project files. KnowledgeStore is directory-scoped. Each directory that contains a .knowledge.yaml file…
cocoscout
Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.
cocohealth
Context utilization monitor — background monitor that samples context window utilization via PostToolUse hook, surfaces advisory at 60% and critical warning with recovery decision matrix at 70%.
pull-search
CocoPull session archive search — full-text search across past sessions. Handles $pull search " " with --since and --feature filters, and $pull index rebuild.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
pod-kb
Display the project knowledge base (lifecycle/kb.md) — project-specific patterns, decisions, and gotchas accumulated by CocoCupper across sessions.