agents-consilium

A way to run other coding agents, including Codex, Claude Code, OpenCode, Grok, and Gemini, as separate reviewers, researchers, or implementers.

In plain words
What is it for?
Use it for multi-agent code review, repository research, delegated implementation, and reconnecting to longer-running agent work.
Why use it?
It lets you obtain independent opinions, investigate a repository with a separate agent, or delegate a coding task while keeping the work organized.

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/codealive-ai/ai-driven-development/agents-consilium
Any agent
npx skills add CodeAlive-AI/ai-driven-development --skill agents-consilium
Clone the repo
git clone --depth 1 https://github.com/CodeAlive-AI/ai-driven-development

Made for: Claude Code, Codex.

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,153 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 $0.00086 $0.03153
Opus 5 $0.00043 $0.01577
Sonnet 5 $0.00017 $0.00631
Haiku 4.5 $0.00009 $0.00315

Measured 2d ago against content hash 567a18a63759, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agents-consilium 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.

The scan reads SKILL.md. This mod also ships 42 executable files (scripts/lib/artifacts.sh, scripts/lib/backend_contract.py, scripts/lib/backend_run.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/agents-consilium/SKILL.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents Consilium

Resolve the entrypoint below, then use only "$CONSILIUM". Select the mode from the user's intent and load only the linked reference needed for that mode.

Entrypoint resolution

Set CONSILIUM to the consilium executable in the scripts subdirectory of the exact SKILL.md loaded by skill discovery. Verify it before the first call:

test -x "$CONSILIUM" || { echo "agents-consilium entrypoint not found: $CONSILIUM" >&2; exit 1; }

Resolve this from the loaded skill path, never from the caller's working directory, repository root, or PATH. Do not execute the entrypoint as a relative path. Keep the shell in the repository the external agent should inspect or change.

Prompt transport is part of the launch

Every review ask invocation must visibly transport a non-empty prompt in the same shell command: as the positional argument, through an explicit stdin pipe or heredoc, or with --prompt-file FILE. Never run a bare review ask command with only options and assume that prompt text from commentary, planning, or the surrounding agent context becomes stdin; shell execution has no such implicit connection. For a generated multiline repository review, prefer an explicit heredoc or prompt file so the complete problem statement and context seed are delivered atomically.

Use these unless the user asks for a different tradeoff:

  • Independent architecture, design, debugging, or planning opinions: review ask --progress compact with all enabled profiles.
  • Routine file or diff review: review code --progress compact (basic: security + correctness).
  • High-risk or release-blocking review: review code --depth super --progress compact.
  • Use specialists only for a broader mid-cost review without an LLM judge. Use ultra only when the user explicitly prioritizes maximum coverage over cost and latency.
  • Repository research: delegate -a grok from the target repository root. Tell the worker whether the task is read-only, keep the default steerable session, and use steer/wait to continue incomplete work.
  • The grok profile is Grok 4.6 and is the default native Grok Build worker. Use the disabled-by-default grok-fast profile explicitly for fast context research with Grok 4.5.
  • Codex Sol is an explicit second opinion for difficult specification verification or optimization planning. Select it with -a codex; do not add it to routine research or the default review pool.

Read the full file on GitHub · 220 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 220 lines · 86 tokens per session scan A 567a18a63759

Subscribe to this mod's changes

agents-consilium is a skill published in the GitHub repository CodeAlive-AI/ai-driven-development (131 stars, last pushed 4d ago), licensed MIT. It adds 86 tokens to every session and 3,153 once invoked, about $0.0004 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

map-auto

Single-entry autonomous autopilot: routes a task through the existing MAP workflows via routetask, then drives the selected chain (map-plan -> map-efficient -> map-check -> map-review, as routed) end-to-end to a committed feature branch in one session, auto-approving routine workflow-control holds and hard-stopping on…

azalio/map-framework · 165 tokens

map-resume

Resume an interrupted MAP workflow from .map/ /stepstate.json checkpoint. Use when returning after context exhaustion, /clear, or a session crash mid-workflow. Do NOT use to start new work; use map-plan or map-efficient.

azalio/map-framework · 53 tokens

map-skill-eval

Evaluate a /map- skill's trigger accuracy and cost. Use when asked to measure skill trigger accuracy, run an eval-set, or check token/duration cost via mapify skill-eval. Do NOT use to plan or implement; use map-plan or map-efficient.

azalio/map-framework · 61 tokens

create-workflows

Creates and revises portable declarative AI workflow files using Markdown frontmatter, DAG nodes, provider IDs, artifact references, imports, reusable inputs, findings artifacts, and review loops. Use when asked to author, improve, modularize, or validate .task.md workflows for CLI-based multi-agent workflow…

crewplaneai/crewplane · 91 tokens

intuitive-doc

Create and maintain an intuitive human documentation surface for AI-agent-developed repos. Use when humans should only need README.md, ARCHITECTURE.md, STATUS.md, and docs/human/ while planning logs, generated docs, retrospectives, ADR detail, and implementation evidence stay in AI-agent-only folders.

MiaoDX/intuitive-flow · 64 tokens

skill-runner

Run a bounded development task through named skills in an isolated, tmux-backed Codex or Claude session. Use for durable or artifact-sensitive worker phases, supervised skill runs, and post-run skill evaluation.

MiaoDX/intuitive-flow · 45 tokens