Chisle
The coding-agent plugin that bills 52% of a bare model across 20 live tasks. Terse persona + tool-output compressor + context diet.
翻訳待ち
A command-line tool that lets coding agents drive Jira issue-tracking workflows — read and search issues via JQL, create, edit, assign and transition them, manage comments, and log work. Jira Cloud an
翻訳待ち
開発ツールGo · ShellGitHub @AngelMsgerオンライン所有者未確認
Have you tried it? One tap is enough. No sign-in needed.
`jira-cli` lets coding agents (Claude Code and others) — and humans — read, search and **maintain** Jira issues from the command line: fetch issues, run JQL searches, create/edit/assign issues, move them through workflow transitions, and manage comments.
翻訳待ち
Loading the full README.
Read the full README ↗Drive Jira issue-tracking workflows from your terminal — built for coding agents.
jira-cli lets coding agents (Claude Code and others) — and humans — read,
search and maintain Jira issues from the command line: fetch issues,
run JQL searches, create/edit/assign issues, move them through workflow
transitions, manage comments, and log work. It speaks to both Jira Cloud (REST v3)
and Data Center / Server (REST v2), returns agent-friendly JSON with
structured errors, and ships a companion Skill that teaches an agent how to
use it. Write commands support --dry-run, and destructive ones require --yes.
📖 Documentation site: https://angelmsger.github.io/jira-cli/
{items, next, has_more} pagination, and
--fields projection so an agent spends minimal context.--dry-run; destructive
commands need --yes.worklog speaks Jira's own units ("3h 20m") and
normalizes --started into the colon-free instant the API demands.
worklog search --since 7d reconstructs a person's week across issues
within a bounded, half-open window..env file,
a YAML config file, or an interactive wizard; secrets stored in the OS
keychain.jira Skill, embedded in the binary, that
guides coding agents through the CLI.Install the CLI with npm, then take two short steps to finish setup — deploy the companion Skill, then (optionally) enable shell completion.
npm install -g @angelmsger/jira-cli
npm downloads the prebuilt binary for your platform, verifies its SHA-256
checksum, and keeps upgrades one npm update -g @angelmsger/jira-cli
away.
go install github.com/angelmsger/jira-cli/cmd/jira-cli@latest # go 1.24+
make install # from a source checkout
Or download a prebuilt binary from the Releases page. The full installation guide covers every method.
The jira Skill is embedded in the binary; it teaches your coding agent
(Claude Code, Codex, Cursor, Agents (shared), Gemini CLI, GitHub Copilot, OpenCode, Continue, Windsurf, Grok Build, Pi, Kilo Code, and Roo Code) how to drive the CLI. skill install probes for
installed agents and installs into each one found:
jira-cli skill install # auto-detect; install for each agent found
jira-cli skill install --agent codex
jira-cli skill status # compare loaded, installed, embedded versions
jira-cli skill uninstall # remove it again
After upgrading the CLI, re-run skill install and reload the agent context.
Details,
including the npx skills workflow, are in
docs/installation.md.
jira-cli completes subcommands, enum flag values and live project keys.
Load the completion script for your shell once:
source <(jira-cli completion bash) # bash, current shell
jira-cli completion zsh > "${fpath[1]}/_jira-cli" # zsh, persistent
fish, PowerShell and persistent setup are covered in docs/installation.md.
jira-cli config init --pretty # interactive TUI setup (recommended for humans)
jira-cli doctor # verify configuration and connectivity
jira-cli issue search --project ENG --assignee me
jira-cli issue get PROJ-123
jira-cli issue transition PROJ-123 --to "In Progress"
jira-cli comment add PROJ-123 --body "Deployed to staging."
jira-cli worklog add PROJ-123 --time-spent "3h 20m" --comment "Traced the retry loop"
jira-cli worklog search --since 7d
Settings resolve in precedence order (highest first): CLI flags → environment
variables (JIRA_*) → .env → ~/.angelmsger/jira/config.yaml → defaults.
See .env.example and
docs/installation.md. Secrets are stored in the OS
keychain. If Windows Credential Manager is unavailable, the fallback is
encrypted with per-user DPAPI; macOS/Linux retain the 0600 fallback. Secrets
are never written to the config file.
This is the beginning of the README. Read the rest at the original. Read the full README ↗