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 skills/riemannulus/knowledge-base/kb-briefnpx skills add riemannulus/knowledge-base --skill kb-briefgit clone --depth 1 https://github.com/riemannulus/knowledge-baseWhat 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 | $0.00102 | $0.00664 |
| Opus 5 | $0.00051 | $0.00332 |
| Sonnet 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 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.
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 ⚠ 알려진 함정 (N건): 각 한 줄 + 예방책 ✔ 관련 결정 (N건): 결정 요지 + superseded 여부 (superseded 뱃지가 있으면 대체본을 봐라) Δ 최근 변경: 관련 파일/영역의 최근 커밋·PR 요지 ?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.
- 2d 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 21d ago), licensed MIT. It adds 102 tokens to every session and 664 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
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.
fortemi-monthly-report
Author a Fortémi monthly report as a docsite blog post — gather what shipped that month from git history, CHANGELOG, and release announcements, then write it up FOR USERS in plain language and publish it to the Pagenary blog collection.
synorive
检索用户本机的内容库 —— 文档、代码、图片里的文字、网页存档、视频台词，都能用中文语义搜。当用户提到"我之前存过""找一下我的""那个文件在哪""我记得看过"这类需要翻自己资料的请求时用它。也能把新文件加入索引、找相似内容、按时间看分布、看实体关系图。不要用于搜索公开网络信息（那是 WebSearch 的活）。.
cocosearch-review-pr
Use when reviewing a GitHub PR or GitLab MR by URL. Fetches diff and metadata via API, then uses CocoSearch for blast radius analysis, dependency impact, pattern consistency, and test coverage assessment. Read-only by default; optionally pushes findings back as inline PR/MR comments after your confirmation.
cocosearch-add-language
Use when adding support for a new programming language or config format to CocoSearch. Guides through all paths (handler, symbol extraction, context expansion) with registration checklists. For grammar handlers, use cocosearch-add-grammar.
cocosearch-add-extractor
Use when adding a dependency extractor for a language or grammar. Guides through pre-checks, extractor implementation, optional module resolver, tests, and registration. Enables deps tree, deps impact, and dependency-enriched search for the target language.