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 skills add riemannulus/knowledge-base --skill kb-briefgit clone --depth 1 https://github.com/riemannulus/knowledge-baseWrote 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/skills/riemannulus/knowledge-base/kb-brief)<a href="https://agentmods.dev/skills/riemannulus/knowledge-base/kb-brief"><img src="https://agentmods.dev/badge/skills/riemannulus/knowledge-base/kb-brief/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/skills/riemannulus/knowledge-base/kb-brief"><img src="https://agentmods.dev/badge/skills/riemannulus/knowledge-base/kb-brief.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 | $0.00102 | $0.00664 |
| Opus 5.5 | $0.00041 | $0.00266 |
| Sonnet 5.5 | $0.00020 | $0.00133 |
| Haiku 4.5 | $0.00010 | $0.00066 |
Grade A, and why
kb-brief 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.
What it actually says
kb-brief — 작업 착수 브리핑
작업 주제를 받아, 코드를 만지기 전에 팀 기억을 조회한다. 목적: 같은 실수 반복 방지 + 이미 내려진 결정과의 충돌 방지.
절차
-
주제 정제: 사용자의 작업 설명에서 검색 키워드 2~3개를 뽑는다 (기능명, 에러 문자열, 파일/모듈명 등. 정확 토큰은 그대로, 개념은 자연어로).
-
병렬 조회 (kb MCP 도구):
pitfalls(topic)— 과거에 밟은 함정 (가장 중요)search(query, limit=5)— 관련 결정·문서·스레드. 관련 파일 경로를 알면search_code(pattern)도 함께recent_changes(days=14)/ (PR 소스가 있으면)recent_prs(query, days=14)who_knows(topic)— 막히면 물어볼 사람
-
작업이 특정 파일을 만진다면: 그 경로가
code_refs로 걸린 learning이 있는지search(경로)로 확인 — "이 파일을 만질 때 알려진 함정"이 최우선 정보다. -
브리핑 출력 (간결하게, 근거는 document_id/URL 인용):
## 착수 브리핑: <주제> ⚠ 알려진 함정 (N건): 각 한 줄 + 예방책 ✔ 관련 결정 (N건): 결정 요지 + superseded 여부 (superseded 뱃지가 있으면 대체본을 봐라) Δ 최근 변경: 관련 파일/영역의 최근 커밋·PR 요지 ? 물어볼 사람: who_knows 상위 1~2명 -
함정·결정이 0건이면 그대로 말하라 — 억지로 채우지 않는다. 0건인 주제는 작업 후 기록할 가치가 높다는 신호다 (kb-log로 이어진다).
주의
- kb MCP가 연결돼 있지 않으면 조회를 건너뛰지 말고 사용자에게 연결을 안내한다
(README §4:
claude mcp add --transport http kb https://.../mcp). - superseded 표시가 붙은 결정을 근거로 삼지 마라 — 대체본(document_id)을 따라가라.
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 First seen · 41 lines · 102 tokens per session scan A 8c5fd6357209
kb-brief is a skill published in the GitHub repository riemannulus/knowledge-base (1 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 664 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
kb-memory
Local-first agent memory and knowledge service (RAG) installed from PyPI. Use when a task needs to store or recall long-term user preferences, project decisions, facts, documents or web pages, when different projects need separate memories, or when the user mentions "kb memory", "kb", or a local MCP memory service.…
check-memory-before-acting
Search this project's own memory before doing something it may already have opinions about. Use before running a build/test/deploy command, before choosing a library or approach, before changing configuration or CI, and before re-opening a decision that may already have been settled. Also use when a task resembles…
re-call
Give an AI agent trusted persistent memory across sessions. Use before planning or answering when earlier runs may contain relevant decisions, failures, experiments, user corrections, unresolved work, or lessons that should influence the current task, and after learning a durable fact that future runs should inherit.
keep-memory-current
Load this project's memory when you start, and write back what you learned before you stop. Use at the beginning of a work session, when finishing a task or about to end a session, after debugging something non-obvious, after a decision that took argument to reach, and whenever you catch yourself thinking "I should…
librarian
File immutable evidence into a small, densely linked shared wiki.
fortemi-roadmap-skill
Advance the Fortemi delivery roadmap by one concrete increment and document the progress. Reads .aiwg/planning/roadmap.md, picks the next actionable item respecting phase gating, does or dispatches the work, then records progress back into the roadmap. Built for fresh sessions and simple loops.