amirkiarafieiamirkiarafiei/subagent-cli-skills/skills/qoder-cli/SKILL.md

qoder-cli

Skill14 starsChanged 10 days agoMITView on GitHub

Use Qoder CLI as a subagent. Lets the main agent prompt Qoder CLI from the terminal in headless mode with the `qodercli` command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to Qoder CLI, when a task needs a second independent agent, or when a plan needs a fresh perspective.

Pipes a download into a shell
Installs packages

In this repository24 other files it gives its agents.
- antigravity-cliSkill
- claude-codeSkill
- cline-cliSkill
- codex-cliSkill
- copilot-cliSkill
- cursor-cliSkill
- deepagents-codeSkill
- devin-cliSkill
- gemini-cliSkill
- goose-cliSkill
- grok-cliSkill
- hermes-agentSkill
- junie-cliSkill
- kilocode-cliSkill
- kimi-codeSkill
- kiro-cliSkill
- mistral-vibeSkill
- oh-my-piSkill
- openclaw-cliSkill
- opencode-cliSkill
- openhands-cliSkill
- pi-cliSkill
- qwen-codeSkill
- <skill-name>Skill

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 8 are distinctive, and 2 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
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

Distinctive:
Secrets or policy-sensitive work: Do not pipe credentials into a subagent.
line 48
Distinctive:
Low return on investment: If writing the handoff costs more than doing the edit, do the edit.
line 50
Distinctive:
Treat every call as stateless delegation: the subagent keeps nothing between calls, so each command must carry its own state.
line 61
Distinctive:
Write the prompt as a transfer of shared state, not as a title.
line 71
Distinctive:
Prefer sequential delegations with explicit carry-over.
line 82
Distinctive:
After the subagent returns:
line 96
Distinctive:
Every vendor has its own terminal rules.
line 104
Distinctive:
Exit code 0 is not success: If stdout is empty, treat the run as failed and read stderr.
line 108
Very specific:
Keep all seven sub-headings, in this order, even if the answer is "none".
line 119
Very specific:
Run qodercli --list-models to see the models available to the authenticated account.
line 175

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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

SKILL.md

Qoder CLI (subagent / task delegation)

<!-- =============================================================================
     GLOBAL HALF — sections 1 to 5.
     These sections are identical in every skill in this repository.
     Copy them without any change. Do not put a vendor name or a flag in them.
     A change here must be made in all skills at the same time.
     ============================================================================= -->

What is it

This skill teaches your agent to use an agent from another vendor as a subagent.

Almost every coding agent has a headless mode. Headless mode runs the agent from the terminal with one command and returns the answer to stdout. This skill gives the command pattern for one such agent, and the protocol to transfer enough context with the task.

You stay the main agent. You keep the plan, the decisions and the conversation with the user. The subagent does one bounded task and reports back.

When to delegate

The user asks for it. The user names another agent, or asks for a second opinion.
Large or multi-step work. The task covers several files, phases or checkpoints.
Code review with a fresh mind. Another agent reviews the work with a different lens and no memory of the decisions that produced it.
Planning that needs different ideas. A second agent proposes options that you did not consider.
An internal council. Several subagents answer the same question, and you compare the answers.
Deep research. The other CLI has web search, web extraction or browser automation.
Background investigation. A long task runs in the background while you continue in the foreground.

When not to delegate

Small or single-step tasks. One or two edits, or a short explanation, are faster in this thread.
Tight feedback loops. The user wants quick back-and-forth in one conversation.
Secrets or policy-sensitive work. Do not pipe credentials into a subagent. Redact first.
Context you already hold. Repeating the whole plan in a prompt adds no value.
Low return on investment. If writing the handoff costs more than doing the edit, do the edit.
Work that needs high precision and full judgement. A subagent without your context will break a task that depends on a detail only this session knows.

Delegation and context transfer protocol

An isolated subagent saves tokens, but it splits the story. The subagent does not see this conversation. It has no memory of the goal you agreed with the user, the decisions you already made, or the paths you agreed not to touch. A poor handoff causes misread tasks, wrong assumptions about the stack or the style, and wasted edits.

Treat every call as stateless delegation: the subagent keeps nothing between calls, so each command must carry its own state. A good handoff happens when you keep these practices in mind:

Shared state handoff. The prompt carries the original goal, the decisions already made, and the explicit scope, to bridge the subagent's missing session history.
Contextual preservation. The high-volume work stays in the isolated process, so the bulk never enters this conversation and no "split story" forms from missing history.
Result reconciliation. What comes back is folded into this thread afterwards, so there is a single source of truth.

Write the prompt as a transfer of shared state, not as a title. Include all six fields:

Include	Why
Goal	The same objective as the user, not only the immediate micro-task.
Decisions	Framework, patterns, naming, "use X not Y" — anything that would otherwise be guessed wrong.
Scope	The absolute paths and modules to touch, and the areas to leave alone. A relative path may not resolve where you expect.
Constraints	Performance, accessibility, compatibility, review gates, "no new dependencies".
Verification	The exact command the subagent must run and pass before it returns.
Output	For example: "report only, no edits", "apply edits with a minimal diff", "list the files changed".

Prefer sequential delegations with explicit carry-over. Parallel runs diverge unless every run gets the same briefing.

Run the subagent in the mode that does the work without asking for approval. Headless mode has nobody to answer a permission prompt. Any mode that stops to ask will stall, or return an empty answer with a success exit code. Each CLI names this mode differently — take the flag from the vendor card below.

Never call a subagent in plan mode. Many CLIs have a plan or read-only mode. That mode makes the other agent write a plan for itself, which is not what you asked for: you want its work or its answer, and you keep the planning. Plan mode also waits for someone to approve that plan, so the run comes back with nothing. If you want no file changes, keep the auto-approving mode and write "report only, no edits" in the Output field. Do not use plan mode to make a run read-only.

After the subagent returns:

Report to the user. Give a short summary. Do not paste long logs unless the user asks.
Reconcile the context. Record the decisions it made, the files it changed, and the open risks, so this session stays the single source of truth.

CLI failure modes

Every vendor has its own terminal rules. A headless run fails quietly more often than it fails loudly.

Wrap the call in an external timeout. A headless CLI can stall before its own timeout starts.
Exit code 0 is not success. If stdout is empty, treat the run as failed and read stderr. A permission the CLI could not ask for, and a prompt that never arrived, both look like success.
Never carry a flag habit from one CLI to another. The same short flag means different things in different tools. In OpenCode, -p is --password: passing a prompt to it empties the message and the run waits on stdin forever. Confirm every flag against the CLI's own --help.
An unrecognized-flag error means this skill is stale, not that the task is impossible. Read --help, continue with the flags that exist, and tell the user which line in this file is wrong.

<!-- =============================================================================
     VENDOR HALF — section 6.
     Everything below is specific to this CLI.
     Keep all seven sub-headings, in this order, even if the answer is "none".
     Take every flag from the installed binary (`<cli> --help`), not from memory
     and not from another skill in this repository.
     ============================================================================= -->

Vendor card

Binary and prompt form

Binary: qodercli
Install: curl -fsSL https://qoder.com/install | bash (recommended native build), or npm install -g @qoder-ai/qodercli (legacy; Node 20+). Official page: https://docs.qoder.com/cli/installation.
Prompt form: flag plus positional. -p/--print is a boolean ("Print response and exit (non-interactive)"); it takes no value. The prompt is the positional [query], so qodercli -p "prompt" works because the next token becomes the query. There is no --prompt option — it gives an unknown-option error. The only other prompt option is -i, --prompt-interactive <text>, which runs the prompt and then stays interactive, so do not use it for delegation.

Headless and output flags

Need	Flag
Run once and exit	`-p`, `--print` (prompt is positional)
Plain text	`-o text` / `--output-format text` (default)
One JSON object	`-o json`
Event stream	`-o stream-json`
Context window	`--context-window <tokens>`
Reasoning depth	`--reasoning-effort <low\|medium\|high\|xhigh\|max>`
List models and exit	`--list-models`

Approvals and permissions

--permission-mode <mode> selects the gate:

Mode	Behavior when approval would be needed, headless
`default`	Auto-runs safe reads/internal ops; sensitive actions need confirmation — not available headlessly, see below
`accept_edits`	Auto-approves in-workspace file edits; shell/external ops still gated
`auto`	An agent-side authorization decision per action, no interactive prompt; a circuit breaker asks for confirmation after too many consecutive blocks
`bypass_permissions` (`--dangerously-skip-permissions`, or the hidden alias `--yolo`)	Skips approval prompts, but destructive operations against the working dir, home dir, filesystem root, or top-level dirs still require confirmation
`dont_ask`	Built for non-interactive workflows: anything that would need approval is denied instead of asked
`plan`	Legacy: maps to `default` plus a read-only work state — do not use for delegation

Critically, the official docs state the headless default explicitly: "Headless (-p/--prompt): Auto-deny. No interaction available; ask becomes deny." (The docs write --prompt there; the binary has no such option, so use -p.) So a plain -p run with no --permission-mode set will silently refuse anything gated — pass --dangerously-skip-permissions for delegation that needs to act, or dont_ask if you want that same deny-everything behavior made explicit. --yolo is the same flag; it works but --help hides it. --allowed-tools / --disallowed-tools and --tools scope which tools are available at all; --max-turns bounds the dialog length (documented in the CLI reference; hidden from --help).

Models and how to list them

Run qodercli --list-models to see the models available to the authenticated account.

Selection is -m/--model <tier-or-name>. Five simplified tiers exist: auto (smart routing, recommended default), performance, efficient, lite (free, Team users), and ultimate (heaviest reasoning). --model also accepts a specific vendor-hosted frontier model identifier directly, as listed by --list-models — do not hardcode one here, since names and credit costs change; check the model docs and Artificial Analysis for current names and pricing.

Command pattern

qodercli -p "GOAL: [goal] | DECISIONS: [decisions] | SCOPE: [paths] | CONSTRAINTS: [constraints] | VERIFICATION: [test_command] | OUTPUT: [format]" \
  --dangerously-skip-permissions --model <tier-or-identifier> -o text 2>&1

Prompt examples

Implement: qodercli -p "GOAL: [goal] | SCOPE: [paths] | VERIFICATION: [test_command] | OUTPUT: [format]" --dangerously-skip-permissions --model efficient -o text
Investigate: qodercli -p "GOAL: Map how [feature] works | SCOPE: [paths] | OUTPUT: concise file:line map" --dangerously-skip-permissions --model efficient -o text
Heavy reasoning: qodercli -p "GOAL: Design architecture for [feature] | SCOPE: [paths] | OUTPUT: architecture plan" --dangerously-skip-permissions --model ultimate --reasoning-effort high -o text

Docs and reference

Flags, model tiers, permission modes, config paths: reference.md
Vendor documentation: https://docs.qoder.com/cli/cli-reference and https://docs.qoder.com/en/cli/permissions
Checked against qodercli 1.1.20 --help on 2026-11-05 (the version installed here). The latest published version is 1.1.83 (npm @qoder-ai/qodercli); it was not run, so newer flags may exist. Docs claims not visible in --help (hidden --yolo and --max-turns, the permissions quote) come from the official documentation.

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