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 commands/study8677/repobrain/rb-refreshgit clone --depth 1 https://github.com/study8677/repobrainWhat 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 | $0.00029 | $0.00375 |
| Opus 5 | $0.00015 | $0.00187 |
| Sonnet 5 | $0.00006 | $0.00075 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
rb-refresh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run the RepoBrain CLI for the current workspace.
通过 RepoBrain CLI 刷新当前工作区知识库。
Use Bash:
rb-refresh --workspace "$PWD"
使用 Bash：
rb-refresh --workspace "$PWD"
If $ARGUMENTS contains quick, add --quick. Quick mode compares only committed
changes, requires a clean worktree, and lets RepoBrain's ImpactPlanner plus an
independent Verifier update only affected Agent groups. It never falls back to
a full refresh. If $ARGUMENTS contains failed-only, add --failed-only to
resume the failed/pending groups for the same target commit.
如果 $ARGUMENTS 包含 quick，追加 --quick。quick 只比较已提交变更，要求工作区
干净，由 RepoBrain ImpactPlanner 与独立 Verifier 只更新受影响 Agent 分组，且绝不
自动降级为全量刷新。如果 $ARGUMENTS 包含 failed-only，追加 --failed-only，
续跑同一目标提交中失败或待处理的分组。
If rb-refresh is not found, tell the user the engine CLI is not installed and suggest:
如果找不到 rb-refresh，说明 engine CLI 尚未安装，建议用户运行：
pipx install "git+https://github.com/study8677/repobrain.git#subdirectory=engine"
Report progress concisely; full refresh can take several minutes.
简洁汇报进度；完整 refresh 可能需要几分钟。
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 · 44 lines · 29 tokens per session scan A eef30501fe64
rb-refresh is a command published in the GitHub repository study8677/repobrain (1,321 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 375 once invoked, about $0.0001 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 commands, from other repositories
codesage-review
Review CodeSage feature slices in parallel and persist validated findings.
codesage-report
Render a Markdown findings report from .codesage/findings/. No LLM call — pure formatter.
codesage-revalidate
Re-check findings after code changes without inferring fixes from omission.
codesage-eval
Evaluate CodeSage effectiveness on a project by mining session-based eval cases and running the bench runner.
codesage-onboard
Onboard a project to CodeSage (global MCP registration, init, index, git hooks, agent hint).
codesage-reset
Drop a project's CodeSage index and rebuild from scratch (use after settings changes, device switches, or corruption).