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 xonovex/platform --skill memory-management-guidegit clone --depth 1 https://github.com/xonovex/platformWrote 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/xonovex/platform/memory-management-guide)<a href="https://agentmods.dev/skills/xonovex/platform/memory-management-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/memory-management-guide/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/xonovex/platform/memory-management-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/memory-management-guide.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 | $0.00101 | $0.00806 |
| Opus 5.5 | $0.00040 | $0.00322 |
| Sonnet 5.5 | $0.00020 | $0.00161 |
| Haiku 4.5 | $0.00010 | $0.00081 |
Grade A, and why
memory-management-guide 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 1mo 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Management Guidelines
General principles for allocating, owning, and freeing memory in manual-memory or buffer-passing code. Language-agnostic; examples are in C. Domain skills (e.g. C99, GPU device memory) keep their own specifics and link here for the underlying principle.
Essentials
- Caller owns memory - APIs take caller-provided storage; never allocate internally, see references/caller-owns-memory.md
- Group by lifetime - Allocate together what dies together; free as a unit, see references/ownership-and-lifetimes.md
- One owner - Exactly one owner frees; everyone else borrows, see references/ownership-and-lifetimes.md
Allocation strategy
- Arena / bump - Pointer-bump from a block; reset frees everything at once, see references/arenas-and-pools.md
- Object pool - Fixed-size slots + free list; O(1) alloc/free, stable, see references/arenas-and-pools.md
- Scratch / temp - Per-frame/per-request arena reset each cycle, see references/arenas-and-pools.md
- Virtual-memory reserve/commit - Reserve a large range, commit pages on demand; stable addresses, no realloc copy, see references/arenas-and-pools.md
- Virtual-memory tricks - Cap-free arrays, page-aligned growth, gapless ring buffers, end-of-page bounds checks, see references/virtual-memory.md
Ownership
- Lifetime by scope - Tie allocation lifetime to a clear scope/phase, see references/ownership-and-lifetimes.md
- Handles over pointers - Reference relocatable storage by index/handle (layout detail in data-oriented-design-guide), see references/ownership-and-lifetimes.md
Gotchas
- Bump allocation has no bounds safety unless you check capacity; always assert/return on overflow.
- Two owners means double-free or leak; decide ownership explicitly, don't infer it.
- Pointers into a growing/reset allocation dangle. Prefer offsets/handles across a boundary (a virtual-memory reserve/commit block is the exception: it never moves).
What ships with it
8 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.
- 1mo ago First seen · 41 lines · 101 tokens per session scan A af4c6775ea7d
memory-management-guide is a skill published in the GitHub repository xonovex/platform (6 stars, last pushed 5d ago), licensed MIT. It adds 101 tokens to every session and 806 once invoked, about $0.0004 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 2026-09-08.
Other skills, from other repositories
boost-modules
Skill "boost-modules" from av/harbor, covering harbor boost custom modules, module structure, quick reference, output methods and stream text to client.
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
memory
Persistent, token-efficient project memory. When ON, maintains a .shob/memory/ folder of structured .md files so the full context of the project is NEVER lost across responses, sessions, or context compaction. Uses progressive disclosure — routes through a lightweight INDEX and loads only the files a task needs…
memory-mine
Mine project files or conversations into the MemPalace memory system. Indexes source code and conversation history as searchable palace drawers with semantic embeddings and room assignment.
aikito
Operate Aikito workspaces and resources, including reading inbox notes, managing memory, skills, projects, MCP servers, subagents, and synchronization.
memorywhale
Query and write durable debugging memory recorded by MemoryWhale. Use when debugging a failure that may have happened before, when you need the exact error/flags/output from an earlier attempt, when the user asks "how did we fix this last time?", or once you've figured out why something failed / how a fix worked and…