agentleFS
Sign inStart free
letya999letya999/opencode-delegate/AGENTS.md

opencode-delegate

AGENTS.md0 starsChanged 31 days agoMITView on GitHub

This repository maintains one portable Agent Skill: opencode-delegate . It runs opencode as a bounded headless delegate and returns a JSON manifest. All maintained repository content is written in English except README.ru.md, the Russian translation. Read SKILL.md, README.md, QUICKSTART.md, scripts/delegate_opencode.py, and references/. - Invoke via python scripts/delegate_opencode.py --cwd <abs-dir> --task <text> [--timeout ...]. - subprocess.run([...], shell=False) only — no shell. - Honor OPENCODE_BIN before PATH and well-known install locations. - Print a JSON manifest; the human-facing result lives under response.…

  • 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 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 repositoryOne other file it gives its agents.

The file

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

6 rules. About 0 are common, 1 is distinctive, and 5 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.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All maintained repository content is written in English except README.ru.md, the Russian translation.

    line 5
  2. Very specific:

    Read SKILL.md, README.md, QUICKSTART.md, scripts/delegate_opencode.py, and references/.

    line 10
  3. Distinctive:

    Default: no auto-approve, no full-access, no permission bypass flags.

    line 26
  4. Very specific:

    Never read or print credentials: API keys, tokens, .env*, auth.json, private keys, browser profiles, vendor credential stores.

    line 27
  5. Very specific:

    Run python -m unittest discover -s tests -v before publishing changes.

    line 34
  6. Very specific:

    Keep index.json and .well-known/agent-skills/index.json in sync.

    line 35

≈ “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

Repository instructions

This repository maintains one portable Agent Skill: opencode-delegate . It runs opencode as a bounded headless delegate and returns a JSON manifest. All maintained repository content is written in English except README.ru.md, the Russian translation.

Read before editing

Read SKILL.md, README.md, QUICKSTART.md, scripts/delegate_opencode.py, and references/.

Wrapper contract

  • Invoke via python scripts/delegate_opencode.py --cwd <abs-dir> --task <text> [--timeout ...].
  • subprocess.run([...], shell=False) only — no shell.
  • Honor OPENCODE_BIN before PATH and well-known install locations.
  • Print a JSON manifest; the human-facing result lives under response.
  • Exit codes: 2 bad cwd, 127 binary missing, 124 timeout, 126 start failure, 65 missing/unusable response after claimed success, else the child process exit code.
  • Temp output dirs use the opencode-delegate - prefix.

Safety posture

  • Default: no auto-approve, no full-access, no permission bypass flags.
  • Never read or print credentials: API keys, tokens, .env*, auth.json, private keys, browser profiles, vendor credential stores.
  • Delegated output is unverified — check git diff and tests before accepting.
  • A delegated agent must not re-delegate to the same CLI in a loop.

Validation and packaging

Run python -m unittest discover -s tests -v before publishing changes. Keep index.json and .well-known/agent-skills/index.json in sync; rebuild dist/ and refresh the sha256 digest whenever the payload changes.

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