imladris: Skill for Claude Code

.agents/skills/imladris-deliberate/SKILL.md

imladris-deliberate is a skill for Claude Code, Codex from FeanorsCodeSL/imladris. It costs 89 tokens per session (864 once invoked), scanned A, original, MIT.

A skill for asking several independent AI models to examine a difficult question, then organizing their agreement, disagreements, missing coverage, and distinct ideas. Imladris is the local service that coordinates this discussion.

In plain words
What is it for?
Use it to compare technical options, review an architecture, investigate a research question, critique an answer, or continue a discussion with the same group of models.
Why use it?
It reduces the risk of relying on one model for research, design choices, comparisons, or critiques where mistakes matter.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is FeanorsCodeSL/imladris's own configuration. It tells Claude Code and Codex how to work on imladris itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything imladris configures →

Reuse

Borrowing it

Nothing to install: this file belongs to FeanorsCodeSL/imladris. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/FeanorsCodeSL/imladris/main/.agents/skills/imladris-deliberate/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/FeanorsCodeSL/imladris

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for imladris-deliberate

README.md
[![agentmods](https://agentmods.dev/badge/skills/feanorscodesl/imladris/imladris-deliberate/github.svg)](https://agentmods.dev/skills/feanorscodesl/imladris/imladris-deliberate)
Your own site
<a href="https://agentmods.dev/skills/feanorscodesl/imladris/imladris-deliberate"><img src="https://agentmods.dev/badge/skills/feanorscodesl/imladris/imladris-deliberate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for imladris-deliberate

Your own site · 80×15
<a href="https://agentmods.dev/skills/feanorscodesl/imladris/imladris-deliberate"><img src="https://agentmods.dev/badge/skills/feanorscodesl/imladris/imladris-deliberate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 864 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00089 $0.00864
Opus 5 $0.00044 $0.00432
Sonnet 5 $0.00018 $0.00173
Haiku 4.5 $0.00009 $0.00086

Measured 10d ago against content hash 071d94182f64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

imladris-deliberate 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 10d 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.

.agents/skills/imladris-deliberate/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Imladris Deliberation

When to use

Reach for Imladris when a task is hard enough that one model's answer is risky: research questions, design/architecture trade-offs, "compare X and Y", expert critique, or anything where being wrong is costly. For quick lookups, answer directly — deliberation costs ~N panel calls + an analysis call.

Quick Start

Imladris is an MCP stdio server — there is no HTTP endpoint, port, or token. Your harness spawns imladris-mcp; call its tools directly. The /council prompt wraps the one-shot flow below. Use /council-session when the user wants a sustained back-and-forth with the same council.

Call the imladris tool:

  • prompt (required), context (optional extra context for every panellist)
  • preset or panel — which of your configured providers answer
  • analysis_model — override which provider runs the analysis judge
  • thread_id — present means session mode; Imladris reads/writes the local ~/.imladris/sessions/<thread_id>.json file and reconstructs messages[]
  • prior_answer — in session mode, pass your previously authored answer for this thread so Imladris can store it as the assistant turn

Inspect configuration and health with imladris_status (resolved roster, roles, presets, budget thresholds, budget estimates — never secrets or env-var names). Clear local session files with imladris_clear_sessions.

Workflow

  1. If meta.ok == 0, every panellist failed and the tool returns a clean meta.failure — say so instead of inventing evidence; let the harness fall back.
  2. Send the user's question as prompt. Add context for files/constraints.
  3. Pick a preset (your configured presets — use a local-only preset when the data must not leave the network) or an explicit panel.
  4. You are the final author. Read the analysis — especially blind_spots and contradictions — and the raw_answers, then write the answer, preserving genuine disagreements and caveats rather than smoothing them away.
  5. For a session, use the same thread_id on each turn and pass your last answer as prior_answer. If the host drops it, Imladris backfills from stored analysis.
  6. When the analysis flags a claim as low-confidence, verify it before relying on it.

Read the full file on GitHub · 62 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. 10d ago First seen · 62 lines · 89 tokens per session scan A 071d94182f64

Subscribe to this mod's changes

imladris-deliberate is a skill published in the GitHub repository FeanorsCodeSL/imladris (4 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 864 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens