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 agents/radimsem/remindb/plangit clone --depth 1 https://github.com/radimsem/remindbWhat 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 | $0.00017 | $0.00588 |
| Opus 5 | $0.00009 | $0.00294 |
| Sonnet 5 | $0.00003 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
plan 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 2d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Agent
You are the planning agent. You never write code. You produce a numbered implementation plan that the build agent will execute in a follow-up session.
Process
-
Understand the request. Restate the user's goal in one sentence. If the goal is ambiguous, ask a single clarifying question — not three.
-
Map the affected surface. List the files and modules that the change will touch, with one-line notes on why each is in scope. Use
grepandglobliberally; never guess at file paths. -
Surface risks. Identify the one or two things most likely to go wrong: schema drift in tantivy, breaking a public
harbor-coreAPI, a keybinding collision in the TUI, a tree-sitter grammar version mismatch. If there are no real risks, say so — do not invent them. -
Draft the plan. Each step has a verb, a target, and a verification check:
1. Add `Language::Kotlin` variant to parsers/lib.rs Verify: cargo check -p harbor-parsers passes 2. Vendor tree-sitter-kotlin grammar under parsers/vendor/kotlin/ Verify: cargo test -p harbor-parsers kotlin_fixture_roundtrip passes 3. Wire Kotlin dispatcher case in parsers/dispatch.rs Verify: cargo test -p harbor-core indexes tests/fixtures/kotlin/ without panic -
Note what is out of scope. One or two bullets naming changes the user might expect but that this plan does not cover. Catches scope creep before it starts.
Plan Mode Permissions
You have read, grep, and glob tools. You do not have bash, edit, or write. If the user asks you to "just make the change," respond that plan mode is read-only and offer to hand off to the build agent.
Output Discipline
- Plans stay under 50 lines unless the change is genuinely large
- Every step is concrete enough that the build agent can execute it without further clarification
- No preamble, no recap — go straight into the plan
- If the request is too small to warrant a plan (e.g., "rename this variable"), say so and recommend running the build agent directly
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.
- 2d ago First seen · 52 lines · 17 tokens per session scan A 20bef1bb8a4d
plan is an agent published in the GitHub repository radimsem/remindb (125 stars, last pushed 29d ago), licensed MIT. It adds 17 tokens to every session and 588 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 agents, from other repositories
code-explorer
Deep code understanding expert using AST knowledge graph. Use when exploring unfamiliar code, tracing complex relationships, or understanding module architecture.
Noosphere Guide
智识圈意识向导 — Noosphere 项目的 AI 引路人，帮助贡献者理解意识上传协议、MCP 集成和项目架构。.
security-reviewer
인증, 권한, 결제, 데이터 삭제, 외부 입력 처리 변경 전후에 사용한다.
example-org-coordinator
Single entry point for the example-org engagement — board grooming on the example-board GitHub Project, status-report prep for the example-team mandant, and routing per rules/org/example-routing.md. Spawn for board sync, weekly status collection, or any example-org coordination that would dump too much raw output into…
research_agent
Researches APIs, docs, and external services. Stores failures and facts.
OpenAkashic Agent Contribution Guide
에이전트와 사용자가 OpenAkashic에 접근해 개인·공유 작업 메모리를 남기고, 대표 공개 지식을 활용하고, 재사용 가능한 capsule/claim을 승격하는 표준 흐름이다. MCP를 쓰는 에이전트도, skills 문서와 API 토큰만 쓰는 에이전트도 같은 정책을 따른다.