opencode-mem is an OpenCode plugin that gives coding agents persistent memory by storing project context in a local vector database. It helps agents retain information across sessions and learn user profiles over time.
Borrowing it
Nothing to install: this file belongs to tickernelz/opencode-mem. 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/tickernelz/opencode-mem/main/AGENTS.mdgit clone --depth 1 https://github.com/tickernelz/opencode-memWrote 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/instructions/tickernelz/opencode-mem/agents-md)<a href="https://agentmods.dev/instructions/tickernelz/opencode-mem/agents-md"><img src="https://agentmods.dev/badge/instructions/tickernelz/opencode-mem/agents-md/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/instructions/tickernelz/opencode-mem/agents-md"><img src="https://agentmods.dev/badge/instructions/tickernelz/opencode-mem/agents-md.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 | $0.00879 | $0.00879 |
| Opus 5.5 | $0.00352 | $0.00352 |
| Sonnet 5.5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
opencode-mem 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 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents working on opencode-mem — a persistent memory plugin for OpenCode (Turso/libSQL vector search, auto-capture, web UI).
Stack & layout
- Runtime / package manager: Bun
- Language: TypeScript (
src/), Svelte web UI (web/) - Tests:
tests/viabun test - Plugin entrypoints:
src/plugin.ts,src/v2/, exports inpackage.json
Commands
bun install
bun test
bun run typecheck
bun run check # format + lint + typecheck
bun run build
bun run web:dev # web UI only
Prefer bun over npm/npx. Use bunx when a one-off binary is needed.
Commits — Conventional Commits only
All commits MUST follow Conventional Commits 1.0.0:
<type>[optional scope]: <description>
[optional body]
[optional footer(s)]
Allowed types
| Type | Use for |
|---|---|
feat |
New user-facing capability (MINOR) |
fix |
Bug fix (PATCH) |
docs |
Docs / README / comments only |
style |
Formatting; no logic change |
refactor |
Internal change; no feat/fix |
perf |
Performance improvement |
test |
Tests only |
build |
Build system / bundling |
ci |
CI workflows / hooks |
chore |
Maintenance, deps, release plumbing |
revert |
Reverts; reference SHAs in Refs: footer |
Rules
- Description: imperative, concise, no trailing period (
fix: harden provider discovery) - Scope (optional): area of the change, e.g.
feat(turso):,fix(ai):,chore(deps): - Breaking changes:
!after type/scope or aBREAKING CHANGE:footer - One logical change per commit when practical
- Do not invent types outside the table above
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 Changed · +88 lines · +783 tokens per session 7b0e33655f72
- 2mo ago First seen · 9 lines · 96 tokens per session scan A c70d69ef45bc
opencode-mem AGENTS.md is an instructions file published in the GitHub repository tickernelz/opencode-mem (1,825 stars, last pushed 2d ago), licensed MIT. It adds 879 tokens to every session, about $0.0035 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 2026-08-30.
opencode-mem AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| opencode-mem AGENTS.mdtickernelz/opencode-mem | Instructions file | 1.8k | 2d ago | MIT | A | 879 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |