agentleFS
Sign inStart free
kessleriokesslerio/dialpad-skill/AGENTS.md

dialpad-skill

AGENTS.md2 starsChanged 52 days agoMITView on GitHub

This is the dialpad-openclaw-skill repo. It contains the Dialpad webhook server, SMS/call enrichment, and OpenClaw hook integration. Keep this file for knowledge useful to almost every future agent session in this project. Do not repeat what the codebase already shows; point to the authoritative file or command instead. Prefer rewriting or pruning existing entries over appending new ones. When updating this file, preserve this bar for all agents and keep entries concise.

  • 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 31,700 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 repository2 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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
  1. Distinctive:

    Wait for the Codex automated review before merging.

    line 10
  2. Distinctive:

    Do not squash-merge until the Codex review has either posted findings (address them first) or reacted with 👍 (no findings).

    line 11
  3. Distinctive:

    If Codex does not review within 10 minutes, proceed without blocking.

    line 12
  4. Very specific:

    After a local wrapper failure in bin/send_sms.py, a claimed approval draft goes back to a retryable state via …

    line 17
  5. Very specific:

    Run tests with uv run --with pytest python -m pytest tests/ -q (system python3 here has no pytest), and unset DIALPAD_WEBHOOK_SECRET first …

    line 18
  6. Distinctive:

    Keep this file for knowledge useful to almost every future agent session in this project.

    line 22
  7. Distinctive:

    Do not repeat what the codebase already shows.

    line 23
  8. Distinctive:

    Prefer rewriting or pruning existing entries over appending new ones.

    line 24
  9. Distinctive:

    When updating this file, preserve this bar for all agents and keep entries concise.

    line 25

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md - Dialpad OpenClaw Skill

Scope

This is the dialpad-openclaw-skill repo. It contains the Dialpad webhook server, SMS/call enrichment, and OpenClaw hook integration.

PR Review Policy

  • Wait for the Codex automated review before merging. Codex reviews are triggered on PR open / ready-for-review.
  • Do not squash-merge until the Codex review has either posted findings (address them first) or reacted with 👍 (no findings).
  • If Codex does not review within 10 minutes, proceed without blocking.

Managed environment & test runner

  • vendor/ is the managed dependency tree for the generated Dialpad CLI — built, not tracked: it is constructed from the pinned, hash-verified requirements.txt by scripts/build_vendor.py during runtime-copy delivery (docs/reference/runtime-copies.md) and before test runs; provenance, upgrades, and verification: docs/reference/vendor-build.md. bin/_dialpad_compat.py and the generated/dialpad facade put it on PYTHONPATH for every CLI subprocess; do not reintroduce ambient uv/PATH dependency discovery — the deployed gateway runtime carries no uv (#155).
  • After a local wrapper failure in bin/send_sms.py, a claimed approval draft goes back to a retryable state via scripts/sms_approval.py:release_agent_direct_send_claim and is never terminally failed; only provider-result failures use fail_agent_direct_send/record_agent_direct_send.
  • Run tests with uv run --with pytest python -m pytest tests/ -q (system python3 here has no pytest), and unset DIALPAD_WEBHOOK_SECRET first — an ambient secret makes the unsigned webhook-handler tests fail at baseline.

Maintaining this file

Keep this file for knowledge useful to almost every future agent session in this project. Do not repeat what the codebase already shows; point to the authoritative file or command instead. Prefer rewriting or pruning existing entries over appending new ones. When updating this file, preserve this bar for all agents and keep entries concise.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free