Skip to content
Agentmart
Submit a tool

renga

File-Based Issue Management — track issues as plain Markdown files in your repo

Skill by shishidosoichiro

IndexedMIT
Write a review

Chalk Labs

Need help deploying renga?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/shishidosoichiro-renga

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

File-Based Issue Management — track issues as plain Markdown files in your repo

Use cases: documents

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/renga

What's inside

Skill name
renga
Description
File-Based Issue Management — track issues as plain Markdown files in your repo
License
MIT
Instructions
223 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# /renga skill

A Claude Code skill for File-Based Issue Management .
All operations are performed by calling the `renga` binary.

## Usage

```
/renga [create] <title>     Create an issue
/renga done <ID>...          Close one or more issues
/renga pending <ID>...      Put one or more issues on hold
/renga in-progress <ID>...  Mark one or more issues as in-progress
/renga reopen <ID>...       Reopen one or more issues
/renga update <ID> ...      Update issue fields
/renga list                 List open, pending, and in-progress issues
/renga show <ID>         Show issue details
/renga help [command]       Show help
```

`create` is optional. `/renga <title>` creates an issue directly.

---

## Agent workflow conventions

These rules apply whenever an AI agent works with renga issues.

**Before starting work**
- Run `renga list` to confirm which issues are open or pending.
- Run `renga show <ID>` on the relevant issue before beginning work.
- Run `renga in-progress <ID>` to mark the issue as in-progress. Do this before writing any code or making changes — not after.

**During work**
- When you make a decision or discover a constraint that is not obvious from the issue title, append it to the issue body under a `## Notes` section using `--body` on create or by editing the file directly.
- Do not delete issue files. Use `renga pending` or `renga done` instead.

**When blocked**
- If you cannot proceed, run `renga pending <ID>` and append the reason under `## Notes` in the issue body.
- Do not leave the issue as `open` when you are unable to complete it.

**After completing work**
- Run `renga validate` before closing any issue. Exit code 1 means errors exist; fix them first.
- Close the issue with `renga done <ID>`. Do not change `status` to `done` by editing the file directly — always use the command.
- Never skip `renga done` and leave the issue as `open` after work is complete.

---

## Rules (all commands)

- If `$ARGUMENTS` is empty, run `renga help` and display the output.
- Pass script error output to the user as-is.

---

## create

If `$ARGUMENTS` starts with `create`, strip it and use the rest as the title. Otherwise use `$ARGUMENTS` as-is.

```
renga create "<title>" [--id <id>] [--slug <slug>] [--priority high|medium|low] [--area <area>] [--milestone <milestone>] [--label <label>]... [--body <text|->] [--dir=true|false]
renga create --json
```

- `--slug`: Kebab-case English slug derived from the title (max 30 chars). Auto-generated from title if omitted.
- `--area`: Infer from context. Use `misc` if unclear.
- `--priority`: Default is `medium`. Use `high` for correctness issues, `low` for suggestions.
- `--label`: Labels to attach (repeatable: `--label bug --label urgent`). A label must not end with `*`. They are added to any `defaults.labels` from `.renga.yml`.
- `--no-default-labels`: Do not attach `defaults.labels` to this issue.
- `--body`: **Always include.** Write a brief description of what needs to be done and why. The title alone is not sufficient.
- `--dir`: Pass `--dir=true` to store the issue as a directory (`N-slug/README.md`) so attachments or notes can live alongside it. Defaults to the flat `N-slug.md` file.
- `--json`: Read one JSON object from stdin. Supported fields are `title`, `id`, `slug`, `priority`, `area`, `body`, `milestone`, `assignee`, `labels`, and `no_default_labels`. Do not combine with field arguments.
- Report the created file path to the user.

---

## done

Moves the file to `issues/done/`.

```
renga done <ID>...
```

Each ID is processed independently. Successes are printed to stdout; failures to stderr. Exits with code 1 if any ID fails.

---

## pending

Moves the file to `issues/pending/`.

```
renga pending <ID>...
```

Each ID is processed independently. Successes are printed to stdout; failures to stderr. Exits with code 1 if any ID fails.

---

## in-progress

Moves the file to `issues/in-progress/`.

```
renga in-progress <ID>...
```

Each ID is processed independently. Successes are printed to stdout; failures to stderr. Exits with code 1 if any ID fails.

---

## reopen

Moves the file to `issues/open/`. Works from any status directory.

```
renga reopen <ID>...
```

From shishidosoichiro/renga, MIT.

More from shishidosoichiro/renga

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 7, 2026 (24 days ago)
Last release
Oct 8, 2026 (22 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from shishidosoichiro

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get renga running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying renga?

CallGet help
Cite this page

renga skill. Agent Mart. https://agentmart.dev/skills/shishidosoichiro-renga (last updated 2026-10-24)