coding-cli

A procedure for handing coding work to an AI command-line tool, such as Claude Code, Gemini CLI, or qodercli, through a manager agent.

In plain words
What is it for?
Use it when a task specification explicitly enables Coding CLI Mode and code must be prepared, transferred, delegated, and checked through the manager.
Why use it?
It gives workers a defined way to prepare a shared workspace, describe the task precisely, delegate the implementation, and review the result.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/agentscope-ai/agentteams/coding-cli
Any agent
npx skills add agentscope-ai/AgentTeams --skill coding-cli
Clone the repo
git clone --depth 1 https://github.com/agentscope-ai/AgentTeams

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,451 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.01451
Opus 5 $0.00015 $0.00726
Sonnet 5 $0.00006 $0.00290
Haiku 4.5 $0.00003 $0.00145

Measured 2d ago against content hash 1ea8272a4bd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coding-cli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

manager/agent/skills-alpha/worker-skills/coding-cli/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coding CLI Delegation

When the Manager assigns you a task with a "## Coding CLI Mode" section in spec.md, you do not write the code yourself. Instead, you:

  1. Understand the task deeply
  2. Prepare the workspace
  3. Generate a precise coding prompt
  4. Delegate execution to the Manager's CLI tool
  5. Review the result

When to Use This Skill

Check spec.md for the task. If it contains ## Coding CLI Mode, use this skill for all code changes.


Step-by-Step Workflow

1. Prepare the Workspace

Set up the workspace directory under the shared filesystem:

workspace="/root/agentteams-fs/shared/tasks/{task-id}/workspace"
mkdir -p "$workspace"

# Clone a repo (example)
git clone <repo-url> "$workspace"

# Or copy existing code
cp -r /path/to/source "$workspace/"

Constraint: The workspace path must be under /root/agentteams-fs/. The Manager accesses the same path via MinIO mirror.

2. Push Workspace to MinIO

Before sending the coding-request, push all workspace files so the Manager can access them:

mc mirror "/root/agentteams-fs/shared/tasks/{task-id}/workspace/" \
  ${AGENTTEAMS_STORAGE_PREFIX}/shared/tasks/{task-id}/workspace/

2b. Check for Processing Marker

Before modifying the workspace or sending a coding-request, check if the task directory is being processed:

# Sync latest state from MinIO
mc mirror "${AGENTTEAMS_STORAGE_PREFIX}/shared/tasks/{task-id}/" \
  "/root/agentteams-fs/shared/tasks/{task-id}/"

# Check for processing marker
if [ -f "/root/agentteams-fs/shared/tasks/{task-id}/.processing" ]; then
    echo "Task directory is being processed. Wait for manager to complete."
    # Do NOT send coding-request yet; wait and retry
fi

If a .processing marker exists, wait for the Manager to complete their operation before sending your request.

3. Generate a High-Quality Prompt

A good prompt includes:

  • Target files: exact paths and relevant line numbers
  • Specific changes: describe what to change, not just why
  • Context: existing code structure, dependencies, interfaces
  • Acceptance criteria: how to verify the change is correct
  • Constraints: languages, frameworks, style conventions, things NOT to change

Read the full file on GitHub · 180 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 180 lines · 30 tokens per session scan A 1ea8272a4bd8

Subscribe to this mod's changes

coding-cli is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,509 stars, last pushed 11d ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,451 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

ship

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, and create a PR. Use for an explicit /ship invocation or when the user requests the full ship, release, or deploy workflow. For an ordinary commit, push, or pull-request publishing request, use the built-in…

GCWing/BitFun · 88 tokens

plan-ceo-review

CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when…

GCWing/BitFun · 143 tokens

design-review

Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…

GCWing/BitFun · 125 tokens

plan-eng-review

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…

GCWing/BitFun · 116 tokens

autoplan

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…

GCWing/BitFun · 152 tokens

retro

Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively…

GCWing/BitFun · 76 tokens