Verify Cozytouch
gduteil/cozytouch
Prove a change to the Cozytouch Home Assistant integration in a real Home Assistant — a throwaway instance against a fake Atlantic cloud served from a diagnostics dump (a fixture or a reporter's)…
Submit a coding task to the ABCA platform via CLI or REST API.
Install Submit Task
$ npx skills add aws-samples/sample-autonomous-cloud-coding-agents --skill submit-task -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install aws-samples/sample-autonomous-cloud-coding-agents submit-task --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/aws-samples/sample-autonomous-cloud-coding-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/abca-plugin/skills/submit-task .claude/skills/submit-task && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "submit-task" agent skill from https://github.com/aws-samples/sample-autonomous-cloud-coding-agents/tree/main/docs/abca-plugin/skills/submit-task into .claude/skills/submit-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "submit-task", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/aws-samples/sample-autonomous-cloud-coding-agents/tree/main/docs/abca-plugin/skills/submit-taskType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add aws-samples/sample-autonomous-cloud-coding-agents --skill submit-task -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install aws-samples/sample-autonomous-cloud-coding-agents submit-task --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aws-samples/sample-autonomous-cloud-coding-agents.git skills-src && mkdir -p .agents/skills && cp -r skills-src/docs/abca-plugin/skills/submit-task .agents/skills/submit-task && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "submit-task" agent skill from https://github.com/aws-samples/sample-autonomous-cloud-coding-agents/tree/main/docs/abca-plugin/skills/submit-task into .agents/skills/submit-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "submit-task", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add aws-samples/sample-autonomous-cloud-coding-agents --skill submit-task -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install aws-samples/sample-autonomous-cloud-coding-agents submit-task --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aws-samples/sample-autonomous-cloud-coding-agents.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/docs/abca-plugin/skills/submit-task .cursor/skills/submit-task && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "submit-task" agent skill from https://github.com/aws-samples/sample-autonomous-cloud-coding-agents/tree/main/docs/abca-plugin/skills/submit-task into .cursor/skills/submit-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "submit-task", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/aws-samples/sample-autonomous-cloud-coding-agents.git --path docs/abca-plugin/skills/submit-task--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add aws-samples/sample-autonomous-cloud-coding-agents --skill submit-task -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install aws-samples/sample-autonomous-cloud-coding-agents submit-task --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aws-samples/sample-autonomous-cloud-coding-agents.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/docs/abca-plugin/skills/submit-task .gemini/skills/submit-task && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "submit-task" agent skill from https://github.com/aws-samples/sample-autonomous-cloud-coding-agents/tree/main/docs/abca-plugin/skills/submit-task into .gemini/skills/submit-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "submit-task", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install aws-samples/sample-autonomous-cloud-coding-agents submit-taskInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add aws-samples/sample-autonomous-cloud-coding-agents --skill submit-task -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/aws-samples/sample-autonomous-cloud-coding-agents.git skills-src && mkdir -p .github/skills && cp -r skills-src/docs/abca-plugin/skills/submit-task .github/skills/submit-task && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "submit-task" agent skill from https://github.com/aws-samples/sample-autonomous-cloud-coding-agents/tree/main/docs/abca-plugin/skills/submit-task into .github/skills/submit-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "submit-task", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add aws-samples/sample-autonomous-cloud-coding-agents --skill submit-task -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install aws-samples/sample-autonomous-cloud-coding-agents submit-task --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aws-samples/sample-autonomous-cloud-coding-agents.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/docs/abca-plugin/skills/submit-task .opencode/skills/submit-task && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "submit-task" agent skill from https://github.com/aws-samples/sample-autonomous-cloud-coding-agents/tree/main/docs/abca-plugin/skills/submit-task into .opencode/skills/submit-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "submit-task", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
submit-task- GitHub stars
- 157
- Token cost
- ~1.6k tokens
- SKILL.md length
- 612 words
- Files
- 1
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- MIT-0
At a glance
Submit a coding task to the ABCA platform via CLI or REST API.
- Works in 6 steps: Determine Workflow → Collect Task Details → Prompt Quality Check → …
- The user says submit a task
- SKILL.md covers Step 1: Determine Workflow, Step 2: Collect Task Details, Step 3: Prompt Quality Check and Step 4: Set Cost Controls, plus 3 more sections
- Calls node, mise and curl
What it does
Submit Task is an agent skill from aws-samples/sample-autonomous-cloud-coding-agents, published by the product's own GitHub organization. Submit a coding task to the ABCA platform via CLI or REST API. Guides prompt quality, workflow selection, and cost controls. Use when the user says "submit a task", "create a task", "run the agent", "send task to agent", "bgagent submit", "new task", "pr iteration", "pr review", "review a PR", "quick submit", "submit to ABCA", or wants to automate coding work.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Pull requests, Budgeting and forecasting and REST APIs. It works with Amazon Web Services. The repository describes itself as: Autonomous background coding agents on AWS. Turn tasks into pull requests via isolated runtimes, with built-in orchestration, observability, and governance. The licence is MIT-0.
When your agent uses it
- The user says submit a task
- Send task to agent
- Wants to automate coding work
Example prompts
- “submit a task”
- “create a task”
- “run the agent”
- “/submit-task”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit cd9bc54. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
nodemisecurl
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Submit Task loads about 1.6k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 612 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from aws-samples/sample-autonomous-cloud-coding-agents at commit cd9bc54, republished under its MIT-0 licence (© aws-samples). 612 words, ~1,593 tokens.
Download SKILL.mdSave it as
.claude/skills/submit-task/SKILL.md (or your agent's skills folder).- name
- submit-task
- description
- Submit a coding task to the ABCA platform via CLI or REST API. Guides prompt quality, workflow selection, and cost controls. Use when the user says "submit a task", "create a task", "run the agent", "send task to agent", "bgagent submit", "new task", "pr iteration", "pr review", "review a PR", "quick submit", "submit to ABCA", or wants to automate coding work.
- argument-hint
- <repo> [description]
Submit a Coding Task
You are helping the user submit a well-crafted coding task to the ABCA platform. Good prompts are critical — the agent works autonomously without asking clarifying questions.
Running the CLI: examples below call
node cli/lib/bin/bgagent.js …from the repo root. In a non-interactive or mise-managed shellnodemay not be onPATH(command not found) — prefix withmise exec --(e.g.mise exec -- node cli/lib/bin/bgagent.js submit …), or use a globalbgagentif installed. Ifcli/lib/bin/bgagent.jsis missing, runmise run buildfirst.
Quick mode: If the user provided a repo and description inline (e.g. "submit task to owner/repo: fix the login bug"), infer the workflow from the description and skip to Step 5:
- PR number or "review PR" →
--review-pr - "iterate on PR" or "fix PR feedback" →
--pr - Just a number →
--issue - Otherwise →
--taskwith the text description
Step 1: Determine Workflow
Use AskUserQuestion to understand what the user wants:
| Workflow | When to use | CLI selector | Outcome |
|---|---|---|---|
coding/new-task-v1 | Implement a feature, fix a bug, refactor code | --issue or --task | Creates a branch + opens a PR |
coding/pr-iteration-v1 | Address review feedback on an existing PR | --pr | Updates the existing PR |
coding/pr-review-v1 | Get a structured code review (read-only) | --review-pr | Posts review comments |
Step 2: Collect Task Details
Based on the workflow, gather:
For coding/new-task-v1:
- Repository (
owner/repo) - GitHub issue number (preferred — agent fetches full context) OR text description
- If using text: the desired end state, scope constraints, acceptance criteria
For coding/pr-iteration-v1:
- Repository (
owner/repo) - PR number
- Optional: Additional guidance ("Focus on security feedback only")
For coding/pr-review-v1:
- Repository (
owner/repo) - PR number
- Optional: Review focus ("Check for SQL injection", "Review test coverage")
Step 3: Prompt Quality Check
Before submitting, validate the prompt against these principles:
Good prompts:
- Describe the desired END STATE, not step-by-step instructions
- Are specific about scope (one logical change per task)
- State preconditions and constraints ("Use React 18, not 19")
- Define verifiable goals ("npm test must pass")
- Provide examples when behavior is ambiguous
- Reference relevant files/modules (not specific line numbers)
Bad prompts (fix these before submitting):
- Too vague: "Fix the bug" -> "Fix 500 on POST /users when email has plus signs"
- Too prescriptive: "Change line 42" -> "Increase auth timeout to 10s for slow connections"
- Kitchen sink: "Fix login, add dark mode, update README" -> Split into separate tasks
- Missing context: "Make it work like the other service" -> Describe explicitly
If the prompt needs improvement, suggest a rewritten version before submitting.
Show full SKILL.md (217 more words)Show less
Step 4: Set Cost Controls
Recommend appropriate limits based on task complexity:
| Task complexity | Suggested max_turns | Suggested max_budget |
|---|---|---|
| Typo/config change | 10-30 | $1-5 |
| Bug fix (clear scope) | 50-100 | $5-20 |
| New feature | 100-200 | $20-50 |
| Large refactor | 200-500 | $50-100 |
| PR iteration | 30-100 | $5-20 |
| PR review | 30-80 | $5-10 |
Step 5: Submit
Via CLI (preferred):
# From the repo root
node cli/lib/bin/bgagent.js submit \
--repo owner/repo \
--issue 42 \
--max-turns 100 \
--max-budget 20 \
--wait # Optional: poll until completionCLI flag reference:
--repo owner/repo(required)--issue N— GitHub issue number (default workflow:coding/new-task-v1)--task "description"— Text description (default workflow:coding/new-task-v1)--pr N— PR number (coding/pr-iteration-v1)--review-pr N— PR number (coding/pr-review-v1)--workflow coding/foo-v1— Explicit workflow override (optional)--max-turns N— Turn limit (1-500)--max-budget N— USD cost limit ($0.01-$100)--idempotency-key KEY— Deduplication key for safe retries--trace— Enable detailed tracing (4 KB preview cap + full NDJSON trajectory upload to S3)--wait— Poll until terminal status--output json|text— Output format
At least one of --issue, --task, --pr, or --review-pr is required.
Via REST API:
curl -X POST "$API_URL/tasks" \
-H "Authorization: $TOKEN" \
-H "Content-Type: application/json" \
-d '{
"repo": "owner/repo",
"issue_number": 42,
"workflow_ref": "coding/new-task-v1",
"max_turns": 100,
"max_budget_usd": 20
}'Step 6: Monitor and Interact
After submission, show how to monitor and steer the task:
# Watch progress in real time (adaptive polling, auto-exits on terminal state)
node cli/lib/bin/bgagent.js watch <TASK_ID>
# Check status snapshot
node cli/lib/bin/bgagent.js status <TASK_ID>
# Steer the agent mid-run (combined-turn acknowledgement)
node cli/lib/bin/bgagent.js nudge <TASK_ID> "Focus on the auth module first"
# View event log
node cli/lib/bin/bgagent.js events <TASK_ID>
# Download execution trace (requires --trace on submit)
node cli/lib/bin/bgagent.js trace download <TASK_ID>
# List running tasks
node cli/lib/bin/bgagent.js list --status RUNNINGTask states: SUBMITTED -> HYDRATING -> RUNNING -> COMPLETED/FAILED/CANCELLED/TIMED_OUT
Input Mode Quick Reference
--issueonly: Issue is well-written with clear requirements--taskonly: Ad-hoc work or pre-issue tasks--issue + --task: Issue context + scope narrowing or extra guidance--pronly: Address all PR review feedback--pr + --task: PR feedback + focused scope--review-pronly: Full structured code review--review-pr + --task: Focused review on specific concerns
© aws-samples, MIT-0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in docs/abca-plugin/skills/submit-task of aws-samples/sample-autonomous-cloud-coding-agents.
Open the folder on GitHubat commit cd9bc54
Compare with similar skills
Submit Task next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Submit Task this skillaws-samples/sample-autonomous-cloud-coding-agents | 157 | — | ~1.6k | Automated safety check: Pass | MIT-0 | |
| Verify Cozytouchgduteil/cozytouch | 128 | — | ~2.7k | Automated safety check: Pass | None | |
| Kql ValidatorAzure/azqr | 794 | — | ~703 | Automated safety check: Pass | MIT | |
| Cdk Contribution Skillcdklabs/cdk-contribution-skill | 110 | — | ~4.6k | Automated safety check: Pass | Apache-2.0 | |
| PR Reviewcdklabs/cdk-nextjs | 110 | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| PR Reviewaws/aws-cdk-cli | 107 | — | ~2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Kql Validator
Azure/azqr
Validate KQL (Kusto Query Language) files used in Azure Quick Review (azqr) against their recommendation definitions.
Cdk Contribution Skill
cdklabs/cdk-contribution-skill
Guide AWS CDK contributions from GitHub issue analysis to PR-ready code.
PR Review
cdklabs/cdk-nextjs
Review the current PR branch and fix the findings in rounds until reviews come back clean.
- Official
PR Review
aws/aws-cdk-cli
AWS CDK CLI general PR reviewer. An agent skill from aws/aws-cdk-cli.
Finding Triage
HacktronAI/skills
Interactively validate and triage Hacktron findings against the actual source code and (optionally) a live deployment, separate true positives from false positives, adjust severity, then either…
More from aws-samples/sample-autonomous-cloud-coding-agents
- Official
Deploy
aws-samples/sample-autonomous-cloud-coding-agents
Deploy, diff, or destroy the ABCA CDK stack. An agent skill from aws-samples/sample-autonomous-cloud-coding-agents.
- Official
Onboard Repo
aws-samples/sample-autonomous-cloud-coding-agents
Onboard a new GitHub repository to the ABCA platform so the agent can target it.
- Official
Setup
aws-samples/sample-autonomous-cloud-coding-agents
Guided installation and first-time setup for ABCA. An agent skill from aws-samples/sample-autonomous-cloud-coding-agents.
- Official
Troubleshoot
aws-samples/sample-autonomous-cloud-coding-agents
Diagnose and fix common ABCA issues: deployment failures, preflight errors, authentication problems, agent failures, and build issues.
- Official
Status
aws-samples/sample-autonomous-cloud-coding-agents
Check ABCA platform status — stack health, running tasks, and recent task history.
Related
Works with
Questions about Submit Task
What does Submit Task do?
Submit a coding task to the ABCA platform via CLI or REST API. Submit Task is an agent skill from aws-samples/sample-autonomous-cloud-coding-agents, published by the product's own GitHub organization. Submit a coding task to the ABCA platform via CLI or REST API.
When should I use Submit Task?
Submit Task fits situations like: the user says submit a task; send task to agent; wants to automate coding work.
How do I install Submit Task in Claude Code?
Run `npx skills add aws-samples/sample-autonomous-cloud-coding-agents --skill submit-task -a claude-code`. Or copy the skill folder (docs/abca-plugin/skills/submit-task in aws-samples/sample-autonomous-cloud-coding-agents) into .claude/skills/submit-task in your project. Claude Code loads it when a task matches its description.
How do I install Submit Task in Codex?
Run `npx skills add aws-samples/sample-autonomous-cloud-coding-agents --skill submit-task -a codex`. Or copy the skill folder (docs/abca-plugin/skills/submit-task in aws-samples/sample-autonomous-cloud-coding-agents) into .agents/skills/submit-task in your project. Codex loads it when a task matches its description.
Can I use Submit Task in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aws-samples/sample-autonomous-cloud-coding-agents --skill submit-task -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/submit-task, .gemini/skills/submit-task, .github/skills/submit-task and .opencode/skills/submit-task in your project.
What does Submit Task need to run?
Going by SKILL.md and its folder, Submit Task needs the command-line tools its instructions call (node, mise and curl).
Does Submit Task access the network?
SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Submit Task safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Submit Task use?
Submit Task is published under the MIT-0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Submit Task use?
About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Submit Task?
Skills that share tags, products or a category with Submit Task: Verify Cozytouch (gduteil/cozytouch, 128 stars), Kql Validator (Azure/azqr, 794 stars), Cdk Contribution Skill (cdklabs/cdk-contribution-skill, 110 stars) and PR Review (cdklabs/cdk-nextjs, 110 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Submit Task?
aws-samples (a GitHub organization, an official publisher) maintains it in aws-samples/sample-autonomous-cloud-coding-agents, which has 157 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 7, 2026.
Source: aws-samples/sample-autonomous-cloud-coding-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.