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/abostrom/lore-skill/lorenpx skills add ABostrom/lore-skill --skill loregit clone --depth 1 https://github.com/ABostrom/lore-skillWhat 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 | $0.00107 | $0.03084 |
| Opus 5 | $0.00053 | $0.01542 |
| Sonnet 5 | $0.00021 | $0.00617 |
| Haiku 4.5 | $0.00011 | $0.00308 |
Grade A, and why
lore 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lore
Lore is Epic's open-source, content-addressed version control system for code and large binary assets. Every payload, tree node, and revision is keyed by its BLAKE3 hash, so a repository is a Merkle DAG: one 32-byte root hash verifies the whole tree. Workspaces are sparse by default and hydrate fragments on demand. Lore is exposed through a single lore CLI and through Python/JavaScript/C#/Go SDKs that all bind to one C ABI — the CLI is just another consumer of that API, not a privileged one.
Verified against Lore CLI 0.8.3+201 on 2026-06-18. SDK repos: lore-python @ 4f90b7f, lore-js @ 396ad34, lore-dotnet @ a56df73, lore-go @ 91ea1c5.
Iron rules
- Every CLI command accepts
--help. Runlore <cmd> --helpbefore guessing flags — flags differ per subcommand and Lore is pre-1.0 (it changes between minor versions). - Don't invent commands or SDK operations. If a verb isn't in the Quick Reference below (or
reference/cli.md), or an op isn't inreference/sdk/model.md, look it up. CLI verb names are NOT the same as SDK operation names — never assumelore commitmaps to a method calledcommit(it'srevision_commit). - Know whether you're offline or online before acting. The
--offlineglobal flag (CLI) /offline=Trueglobal arg (SDK) is load-bearing. Local-only work (create, stage, commit, branch, diff against cached data) needs no network; push/clone/sync against a remote do. Offline mode never makes network round-trips and never lazy-fetches. - SDK calls bracket their lifecycle:
log_configurefirst,shutdownlast. Every operation isLore.<op>(globals, args).callback(handler).wait(). Skippingshutdownleaks the native runtime.
Detection gate
Before doing anything, confirm the environment. If a precondition is missing, stop and tell the user — never silently fall back to git or Perforce.
- CLI work: is
loreonPATH? (lore --version→ expectlore 0.8.3+...). If not, it's not installed →reference/setup.md. - In a repo? Is the cwd (or
--repository <path>) a Lore repo? A repo has a.lore/directory.lore statusconfirms it. If not, the user needslore repository create/lore clonefirst. - SDK work: is the language binding installed (e.g.
pip install lore-vcsfor Python)? The native lib must be reachable — building the Python types from source needsLORE_BUILD_PATHset to the liblore install. If the binding/lib is absent → stop and tell the user; do not hand-roll FFI.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 145 lines · 107 tokens per session scan A 80018ab91096
lore is a skill published in the GitHub repository ABostrom/lore-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 3,084 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
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
social-post
學習使用者的 Facebook／Instagram／YouTube／Threads／X 語氣與受眾，規劃、撰寫、確認後發佈內容；以已登入 Chrome 受控掃描、草擬及回覆 FB／IG／Threads 留言；並作為流量、留存與轉化的結構化帳本。使用者說「發文」「用我的口氣」「回覆留言」「自動回留言」「掃留言」「查流量」「演算法」「把數據訓練進去」「比較貼文」「優化 pattern」時使用。.
privacy-eu
EU 사용자 대상 서비스용 Privacy Notice·Terms of Service·Consent Modal·Cookie Banner 자동 생성. GDPR (Regulation 2016/679) + ePrivacy Directive + Consumer Rights Directive 2011/83 + Digital Services Act + Digital Content Directive + Unfair Terms Directive 반영. 영문 인터뷰로 진행.
privacy-terms
처리방침·이용약관 자동 생성 진입점. 호출 즉시 6개 하위 스킬(privacy-kr·privacy-eu·privacy-us·privacy-jp·privacy-global·privacy-global-jp)을 번호 메뉴로 제시하고, 번호 입력 즉시 해당 스킬 인터뷰로 직행한다.
higgsfield-troubleshoot
Use when a Higgsfield generation fails, produces poor quality, looks wrong, doesn't match the prompt, or the user needs to fix or improve an output.
higgsfield-motion-design
End-to-end motion-design / animated-ad creation flow on Higgsfield via the MCP connector. Use when the user wants to create motion design, animate a logo, make a video from an image, build an animated ad or brand promo, turn a product into motion, or says 'make a motion', 'motion design', 'animate this', 'make a video…