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 lokikill123/codex-token-skills --skill memorygit clone --depth 1 https://github.com/lokikill123/codex-token-skillsWrote 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/lokikill123/codex-token-skills/memory)<a href="https://agentmods.dev/skills/lokikill123/codex-token-skills/memory"><img src="https://agentmods.dev/badge/skills/lokikill123/codex-token-skills/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 | $0.00035 | $0.00272 |
| Opus 5 | $0.00017 | $0.00136 |
| Sonnet 5 | $0.00007 | $0.00054 |
| Haiku 4.5 | $0.00003 | $0.00027 |
Grade A, and why
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 7d 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.
What it actually says
Memory
Memory File
C:\Users\lokik.codex\MEMORY.md
On Conversation Start (MUST DO FIRST)
Read the memory file. If it doesn't exist, create empty and note "no prior memory".
During Conversation (MUST DO)
When any of these happen, APPEND to MEMORY.md immediately:
- User states a preference or habit
- A project is created or its structure changes significantly
- User gives feedback about your behavior
- A decision is made that affects future work
- Skills are installed or modified
- Important file paths or configs are established
Format
Append entries as: `
YYYY-MM-DD
- [category] fact `
Categories: pref (preference), proj (project), skill (skill), cfg (config), decision
Rules
- Append only. Never delete old entries.
- One line per fact. Be specific.
- If user contradicts old memory, append correction, don't delete old.
- Don't write trivial/temporary facts.
- Max 20 most recent entries. Archive older to MEMORY_archive.md.
What ships with it
1 file 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.
- 7d ago First seen · 40 lines · 35 tokens per session scan A e3497907fcaa
memory is a skill published in the GitHub repository lokikill123/codex-token-skills (111 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 272 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 2026-08-30.
Other skills, from other repositories
notes-keeper
Read, search, and write notes in the opendray file-system vault. Use this whenever the user mentions "notes", "daily log", "project doc", "TODO list", or wants to persist context that should survive across sessions.
claude-jsonl-compressor
Compress one Claude Code JSONL session with strict active-branch isolation, model-authored semantic summaries by default, recent raw context for rewind, validated compact-style output, transactional backup/replacement for one live .claude/projects file, and an independent byte-preserving Read.pages compatibility…
shift-notes
Write and read the between-session handoff file so a fresh agent with no memory can pick up where the last one stopped without re-deriving context. Structured prose, not JSON — the model writes prose better.
context-budget
Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.
context-engineering
A project documentation framework that records a project's goals, requirements, roadmap, and current state in separate files. It also keeps those documents within set size limits for an AI coding agent.
error-experience-library
An error knowledge base that stores recurring error patterns, their causes, and the fixes that worked. It can search past entries and track whether each suggested fix succeeded.