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 instructions/ngvoicu/opencode-claude-code-memory/agents-mdgit clone --depth 1 https://github.com/ngvoicu/opencode-claude-code-memoryWhat 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 | $0.00213 | $0.00213 |
| Opus 5 | $0.00106 | $0.00106 |
| Sonnet 5 | $0.00043 | $0.00043 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
opencode-claude-code-memory AGENTS.md 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- opencode-claude-code-memory CLAUDE.md — 100% identical, 0 lines differ
What it actually says
CLAUDE.md — opencode-claude-code-memory
Byte-identical in CLAUDE.md and AGENTS.md. Read ../CLAUDE.md (workspace identity hub) first.
An OpenCode plugin (plain Node, index.js) that shares Claude Code's local memory with OpenCode: loads Claude Code memory into OpenCode sessions, lets OpenCode read/update the same files, and keeps that shared memory available across longer conversations. See README.md for usage.
Conventions
- origin = NAS (
ssh://zeenas/volume1/git/ngvoicu/opencode-claude-code-memory.git); add a GitHub upstream only if/when it goes public. - Tests in
test/— run them after changes (npm test). - It manipulates the user's real
~/.claudememory files — be conservative: never delete or rewrite memory content wholesale; additive edits only, and respect Claude Code's memory file format (frontmatter + MEMORY.md index).
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 · 12 lines · 213 tokens per session scan A 37f2ef4f1879
opencode-claude-code-memory AGENTS.md is an instructions file published in the GitHub repository ngvoicu/opencode-claude-code-memory (2 stars, last pushed 10d ago), licensed MIT. It adds 213 tokens to every session, about $0.0011 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 instructions, from other repositories
opencode-cache-hit AGENTS.md
Instructions for zhumengzhu/opencode-cache-hit, covering agents.md — maintainer & ai assistant guide, project purpose, documentation map, commands and code conventions.
FlowDeck AGENTS.md
Instructions for DVNghiem/FlowDeck, covering agents.md, 0. non-negotiables, 1. before writing code, 2. writing code: simplicity first and 3. surgical changes.
FlowDeck CLAUDE.md
Instructions for DVNghiem/FlowDeck, covering 1. think before coding, 2. simplicity first, 3. surgical changes, 4. goal-driven execution and agent skills.
campy AGENTS.md
Instructions for dropdevrahul/campy, covering campy - opencode pets plugin, project overview, available pets, file structure and commands.
super-backlog CLAUDE.md
Instructions for adam-s-k-i/super-backlog: This project uses the combined Backlog.md + Superpowers workflow. Read the integration block in AGENTS.md (section between SUPER-BACKLOG markers) and follow it. Tasks are managed exclusively through the backlog CLI.
campy CLAUDE.md
Instructions for dropdevrahul/campy, covering claude.md, installing into an agent, state-file bus, common commands and ghost-pet (legacy bash plugin) — requires jq.