Borrowing it
Nothing to install: this file belongs to divinevideo/divine-mobile. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/divinevideo/divine-mobile/main/.agents/skills/divine-context/SKILL.mdgit clone --depth 1 https://github.com/divinevideo/divine-mobileWrote 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/divinevideo/divine-mobile/divine-context)<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/divine-context"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/divine-context.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 77 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00095 | $0.01635 |
| Opus 5 | $0.00048 | $0.00817 |
| Sonnet 5 | $0.00019 | $0.00327 |
| Haiku 4.5 | $0.00010 | $0.00163 |
Grade A, and why
divine-context 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 7d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Divine Context
The divine-context repo is the cross-repo handbook for the diVine platform. Every divine-* repo's AGENTS.md should pull in @../divine-context/AGENT_CONTEXT.md, but if it doesn't, load it manually before doing real cross-repo work.
On disk
Cloned as a sibling of the current repo:
~/code/divine/
├── divine-context/ ← read this
├── divine-web/
├── divine-mobile/
├── divine-funnelcake/
└── ... (~50 divine-* repos)
If divine-context isn't cloned:
(cd ~/code/divine && [ -d divine-context ] || gh repo clone divinevideo/divine-context)
Reading divine-context
For everyday work, AGENT_CONTEXT.md is enough. It links out to deeper files:
| File | Read when |
|---|---|
AGENT_CONTEXT.md |
Always — single-page primer |
PROJECT.md |
Need product context (what diVine is, who it's for) |
ARCHITECTURE.md |
Touching cross-service flows |
PROJECTS.md |
Asking "is there already a service for X?" |
NOSTR.md |
Publishing/querying/signing Nostr events |
GLOSSARY.md |
Hit an unfamiliar term |
ANDOTHERSTUFF.md |
Need parent-org context |
These files describe state at the time they were written. If a file in a divine-* repo contradicts divine-context, trust the code — and if the contradiction is durable, propose a divine-context update (see below).
Updating divine-context
When you learn a cross-repo fact while working in a divine-* repo, propose it back. Cross-repo means: would an agent in a different divine-* repo benefit from knowing this? If no, it stays in this repo's AGENTS.md or .claude/rules/.
Workflow
- Read this repo's key files (5 min, no deep dive):
README.md,AGENTS.md,.claude/rules/*,docs/**,package.json/Cargo.toml/pubspec.yaml/go.mod, top-levelsrc/. - Read every divine-context file (they're short).
- Build a proposal list — for each item: one line of what, one line of evidence (
path:linein this repo). - Show the proposal list to the user before editing anything. Wait for approval.
- For approved items only, branch from
origin/main(not local main, which may be stale) and make the edits:
Use a worktree inside the divine-context checkout. Other agents may be editing divine-context concurrently; isolating in a worktree avoids branch-state collisions. Put it incd ~/code/divine/divine-context git fetch origin main git worktree add .claude/worktrees/dc-<topic> -b update-from-<thisrepo>-<topic>-$(date +%Y-%m-%d) origin/main # edit files cd .claude/worktrees/dc-<topic> git add <only the files you changed> # never -A git commit -m "<short desc>: <what changed>" git push -u origin HEAD gh pr create --title "..." --body "...".claude/worktrees/(gitignored there) — not/tmp. On macOS/tmpis swept, and a worktree there takes any uncommitted work with it; seeWORKTREES.mdin divine-context. Remove it withgit worktree removeonce the PR merges, since nothing cleans it up for you. - One logical change per PR. Five unrelated improvements = five PRs.
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.
- 7d ago First seen · 115 lines · 95 tokens per session scan A a45d3cb97caf
divine-context is a skill published in the GitHub repository divinevideo/divine-mobile (265 stars, last pushed today), licensed MPL-2.0. It adds 95 tokens to every session and 1,635 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…