marketing-skills / app
AGENTS.md73 starsChanged 3 days agoMITView on GitHub
This project deploys to Graphed cloud from graphed.yaml. It is the Post Engagers lead list. The page at / is a Next.js client component. Keep its behavior. Do not wrap it in a scaffold sidebar. - Never guess manifest fields or CLI flags. Run graphed docs manifest or graphed <command> --help first. - Use graphed --format json when you need to parse output. - Migrations are TypeScript Kysely modules, modeled on packages/core/src/migrations/0001_post_engagers.ts. Register a new file in packages/core/src/db/migrate.ts. Never edit…
- Reads credentials
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 32,671 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository14 other files it gives its agents.
- skills/ad-spy/app/AGENTS.mdAGENTS.md
- skills/enrichment-tables/app/AGENTS.mdAGENTS.md
- skills/ugc-studio/app/AGENTS.mdAGENTS.md
- ad-spySkill
- analytics-dashboardSkill
- enrich-linkedin-engagersSkill
- enrichment-tablesSkill
- feedbackSkill
- post-engagersSkill
- post-to-videoSkill
- static-adsSkill
- tesseract-motionSkill
- ugc-studioSkill
- ugc-videoSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 5
Do not wrap it in a scaffold sidebar.
- Very specific: line 9
Never guess manifest fields or CLI flags: Run graphed docs manifest or graphed <command> --help first.
- Very specific: line 11
Use
graphed --format json: when you need to parse output.
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AGENTS.md
This project deploys to Graphed cloud from graphed.yaml. It is the Post Engagers
lead list. The page at / is a Next.js client component. Keep its behavior.
Do not wrap it in a scaffold sidebar.
Golden rules
- Never guess manifest fields or CLI flags. Run
graphed docs manifestorgraphed <command> --helpfirst. - Use
graphed --format jsonwhen you need to parse output. - Migrations are TypeScript Kysely modules, modeled on
packages/core/src/migrations/0001_post_engagers.ts. Register a new file inpackages/core/src/db/migrate.ts. Never edit a migration that has already been applied. Apply withnpm run db:migrate(also the deploy release command). - Never read
process.envdirectly in app code. Env goes throughpackages/core/src/config.ts(envSlice()/coreEnv()). - One database. Dashboard routes and the worker use
initDb()/getDb().DATABASE_URLselects Postgres. When it is unset, the process uses embedded PGlite sonpm testneeds no database server.
Project shape
One npm workspace (packages/*).
packages/core(@app/core) — schema, scrape queue, worker, email waterfall, tracker.packages/dashboard(@app/dashboard) — Next.js App Router.app/page.tsxrenders the lead list.app/api/[...path]/route.tsis the JSON API.- The worker starts inside the Next server (
packages/dashboard/boot.ts). It is not the cron job. Thetrackcron only queues posts (node cli.mjs track check). cli.mjsqueues work and reads results. It does not scrape. The web worker does.
UI
The lead list is React in packages/dashboard/components/app.tsx, styled by
app/post-engagers.css. Hash routes: #/ new scrape, #/tracking, #/people,
#/posts, #/job/<id>, #/tracked/<id>. Ask your agent in the top bar copies
agentPrompt() from packages/core/src/prompt.ts. The skill tells the agent to
queue the first post or tracked profile from the terminal.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

