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/zhumengzhu/opencode-cache-hit/agents-mdgit clone --depth 1 https://github.com/zhumengzhu/opencode-cache-hitWhat 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 | $0.01522 | $0.01522 |
| Opus 5 | $0.00761 | $0.00761 |
| Sonnet 5 | $0.00304 | $0.00304 |
| Haiku 4.5 | $0.00152 | $0.00152 |
Grade A, and why
opencode-cache-hit 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 3d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — maintainer & AI assistant guide
Instructions for humans and coding agents working in opencode-cache-hit. End-user docs: README.md · README.zh-CN.md.
Project purpose
OpenCode TUI sidebar plugin: cache hit rate, tokens, cost, with sub-agent (child session) rollup. Optional per-call JSONL timeline (timeline.enabled).
Not a fork of opencode-visual-cache. UI patterns and src/tui-panel/ are heavily inspired by visual-cache; product focus differs (see README comparison table).
Documentation map
| Topic | English | 中文 |
|---|---|---|
| Users | README.md | README.zh-CN.md |
| Architecture | docs/en/design.md | docs/zh-CN/design.md |
| Timeline / JSONL | docs/en/timeline.md | docs/zh-CN/timeline.md |
| Token Speed | docs/en/token-speed.md | docs/zh-CN/token-speed.md |
| TTFT Hybrid | docs/en/ttft-hybrid.md | docs/zh-CN/ttft-hybrid.md |
| TTFT Troubleshooting | docs/en/ttft-troubleshooting.md | docs/zh-CN/ttft-troubleshooting.md |
| Dynamic pricing (plan) | — | docs/zh-CN/dynamic-pricing-plan.md |
| TUI panel | src/tui-panel/README.md | src/tui-panel/README.zh-CN.md |
| Migration plan | docs/en/frontend-migration-plan.md | docs/zh-CN/frontend-migration-plan.md |
| Contributing / npm | CONTRIBUTING.md | — |
| Index | docs/README.md |
Commands
bun test # full unit + module-load smoke
bun run check # same as test
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.
- 3d ago First seen · 77 lines · 1,522 tokens per session scan A 0f4c16ff1d70
opencode-cache-hit AGENTS.md is an instructions file published in the GitHub repository zhumengzhu/opencode-cache-hit (23 stars, last pushed 8d ago), licensed MIT. It adds 1,522 tokens to every session, about $0.0076 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 instructions, from other repositories
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.
opencode-claude-code-memory AGENTS.md
AGENTS.md instructions for ngvoicu/opencode-claude-code-memory, covering claude.md — opencode-claude-code-memory and conventions.
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.