agentleFS
can4hou6joeng4can4hou6joeng4/boss-agent-cli/llms.txt

boss-agent-cli

llms.txt2.1k starsChanged 30 days agoMITView on GitHub

A BOSS Zhipin (BOSS 直聘) CLI for people and AI agents. Job discovery with real welfare filtering, applications, recruiter workflows, resumes, AI assistance and recoverable crawling share one capability set behind a single JSON envelope. Current version: 3.0.0. Run boss schema (also supports --format native | openai-tools | anthropic-tools | mcp-tools). 39 top-level commands, 14 first-level recruiter subcommands, 78 implemented MCP tools. The sole registered platform is zhipin (BOSS Zhipin). Every command emits exactly one JSON envelope to stdout: {ok,…

We split this llms.txt into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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
  1. Very specific:

    Run boss schema (also supports --format native | openai-tools | anthropic-tools | mcp-tools).

    line 7
  2. Very specific:

    Every command emits exactly one JSON envelope to stdout: {ok, schema_version, command, data, pagination, error, hints}.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 3,225 llms.txt 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
llms.txt
# boss-agent-cli

> A BOSS Zhipin (BOSS 直聘) CLI for people and AI agents. Job discovery with real welfare filtering, applications, recruiter workflows, resumes, AI assistance and recoverable crawling share one capability set behind a single JSON envelope. Current version: 3.0.0.

## Capability source of truth

Run `boss schema` (also supports `--format native | openai-tools | anthropic-tools | mcp-tools`). 39 top-level commands, 14 first-level recruiter subcommands, 78 implemented MCP tools. The sole registered platform is zhipin (BOSS Zhipin).

## Start here

- [Agent quickstart](docs/agent-quickstart.md) — envelope contract, error recovery, risk-stop rules
- [Command reference](docs/commands.md)
- [Capability matrix](docs/capability-matrix.md)
- [Getting started](docs/getting-started.md)
- [Troubleshooting](docs/troubleshooting.md)

## Install

- MCP server: `uvx --from boss-agent-cli[mcp] boss-mcp`
- CLI: `uv tool install boss-agent-cli`
- Browser core (login / export only): `patchright install chromium`

## Contract

Every command emits exactly one JSON envelope to stdout: `{ok, schema_version, command, data, pagination, error, hints}`. Logs and terminal displays go to stderr. `exit 0` ⇔ `ok=true`; `exit 1` ⇔ `ok=false` by default — opt-in `--exit-codes sysexits` maps error classes to sysexits codes (77 auth, 75 temp-fail, 78 config, 69 unavailable). Errors carry `code`, `recoverable` and `recovery_action`.

## Boundaries

Platform risk codes or security pages stop the workflow and save a checkpoint; resume is explicit and user-driven. Do not bypass risk controls, parallelize requests, or retry indefinitely. Local-first: no telemetry, data stays on this machine.

## Links

- GitHub: https://github.com/can4hou6joeng4/boss-agent-cli
- PyPI: https://pypi.org/project/boss-agent-cli/
- Project site: https://can4hou6joeng4.github.io/boss-agent-cli/

Download now (ZIP)

Trending

Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data

Week of Aug 30: 0 new projectsWeek of Sep 6: 0 new projectsWeek of Sep 13: 0 new projectsWeek of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 0 new projects
Aug 2026Sep 2026Oct 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 0 in all, so this is a hint, not a trend.
  • In this repositoryOne other file it gives its agents.

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.