VoxCircuit
AGENTS.md2 starsChanged 3 months agoMITView on GitHub
This is a security-sensitive, multi-tenant Next.js application. Read the relevant local Next.js documentation before changing Next APIs or routing conventions. Discover -> audit -> plan -> implement -> test -> review diff -> document -> commit. Keep changes focused and do not reset, force-push, delete data, or discard user work. Run the smallest relevant tests first, then npx prisma validate, lint, typecheck, and the affected suite. Review git diff --check. Browser tests must target a VoxDesk server, not another project…
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 31,542 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 repository8 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- browser-verificationSkill
- database-migration-safetySkill
- demo-data-integritySkill
- github-authorship-auditSkill
- portfolio-captureSkill
- security-auditSkill
- voice-provider-reviewSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 1 is common, 1 is distinctive, and 2 are very specific to this project.
≈1
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
- could be automatic: a setting could enforce it
- Very specific: line 16
Use additive migrations and review SQL.
- Common: line 17
Never invent data, weaken auth, bypass security validation, commit secrets, or claim provider verification without an authorized test.
- Very specific: line 21
Run the smallest relevant tests first, then npx prisma validate, lint, typecheck, and the affected suite.
- Distinctive: line 25
Update docs when behavior, provider boundaries, activation requirements, migration delivery, or user-visible capability state changes.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 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
VoxDesk Engineering Instructions
This is a security-sensitive, multi-tenant Next.js application. Read the relevant local Next.js documentation before changing Next APIs or routing conventions.
Working loop
Discover -> audit -> plan -> implement -> test -> review diff -> document -> commit. Keep changes focused and do not reset, force-push, delete data, or discard user work.
Non-negotiable boundaries
- Resolve session, membership, role, workspace, then resource. IDs never grant authority.
- Models request actions; server-owned tools authorize, validate, apply idempotency, and persist safe results.
- Provider webhooks require raw-body verification, timestamp/replay checks, event identity, prompt acknowledgement, and asynchronous projection.
- Simulation is explicit and authenticated. It never calls Telnyx or enters public provider webhook routes.
- Telnyx is the production PSTN/SIP boundary and ElevenLabs is the conversational boundary. Keep provider code out of UI components.
- Use additive migrations and review SQL. Never use
db pushfor production delivery. - Never invent data, weaken auth, bypass security validation, commit secrets, or claim provider verification without an authorized test.
Verification
Run the smallest relevant tests first, then npx prisma validate, lint, typecheck, and the affected suite. Review git diff --check. Browser tests must target a VoxDesk server, not another project sharing the local port.
Documentation
Update docs when behavior, provider boundaries, activation requirements, migration delivery, or user-visible capability state changes. Use the vocabulary: implemented, configured, verified, simulated, activation-required, and planned.
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.

