What is one-turn-proposal?

A method for turning a complex or unclear request into a clear proposal in one response. It helps an agent understand the real need, make a reasoned recommendation, and explain boundaries.

Use it for ambiguous decisions, project proposals, framework design, evaluation, and other requests where the user needs judgment and a usable plan.

It reduces vague answers by requiring the response to take a position, structure the problem, and suggest a practical next step.

one-turn-proposal — Skill for Claude Code and Codex by theseussss

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.

Any agent

npx skills add theseussss/roamfound --skill one-turn-proposal

Clone the repo

git clone --depth 1 https://github.com/theseussss/roamfound

Made for: Claude Code, Codex.

Or install jiacong-flow, the plugin that ships this one along with the rest of its 2 skills, 1 command.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/theseussss/roamfound/one-turn-proposal.svg)](https://agentmods.dev/skills/theseussss/roamfound/one-turn-proposal)

Your own site

<a href="https://agentmods.dev/skills/theseussss/roamfound/one-turn-proposal"><img src="https://agentmods.dev/badge/skills/theseussss/roamfound/one-turn-proposal.svg" alt="Measured on agentmods" height="20"></a>

Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,675 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.

Model	Per session	Once invoked
Fable 5.1	$0.00106	$0.01675
Opus 5	$0.00053	$0.00838
Sonnet 5	$0.00021	$0.00335
Haiku 4.5	$0.00011	$0.00168

Measured 8d ago against content hash 58ccae2eadb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

one-turn-proposal 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 8d 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.

skills/one-turn-proposal/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

One Turn Proposal

Use this skill to turn a complex or ambiguous user request into a clear, judgment-led, proposal-grade answer in one response. The goal is not to constrain the model with a rigid template; the goal is to make the answer feel like a capable advisor who understands the request, takes a position, structures the problem, proposes a path, states boundaries, and leaves a useful next interaction point.

This skill can also operate as a methodology system: when the user is designing, evaluating, or formalizing a framework, map the relevant theories into operating roles, preserve traceability, identify intentional exclusions, and expose only the level of structure that helps the user act.

When this skill is used inside a smarter-project managed project, treat smarter-project as the project-state authority. Shape the proposal, evidence logic, and decision structure here; write durable project state only through smarter-project scratch/card/tasks rules and scripts.

Core rule

For every non-trivial request, complete this loop:

Reconstruct the user's real need, not just their surface wording.
Identify the task type and answer depth needed.
Give a clear judgment early.
Structure the problem around the judgment.
Propose a concrete path, not just a list of ideas.
State key risks, assumptions, and boundaries.
End with one useful next step or interaction entry.

Do not expose hidden chain-of-thought. Provide concise reasons, trade-offs, evidence, assumptions, and decision logic that are safe and useful to the user.

Methodology-system architecture

Treat the skill as a layered system, not a single template:

core protocol: the default answer loop in references/core-protocol.md.
complexity router: answer depth selection in references/complexity-levels.md.
task adapters: domain-specific structures in references/task-adapters.md.
methodology system: system positioning, modes, semantic-preservation rules, and versioning in references/methodology-system.md.
methodology map: source-framework traceability in references/framework-map.md.
hidden mechanisms: internal routing, comparison, verification, and self-repair in references/hidden-mechanisms.md.
evidence and retrieval governance: retrieval triggers, source appraisal, and completeness awareness in references/evidence-retrieval-protocol.md, references/source-critical-appraisal.md, and references/search-completeness-awareness.md.
output templates and contracts: natural-language templates in references/response-templates.md, optional machine-readable fields in references/structured-output-contract.md, and optional json schema in schemas/one-turn-proposal.schema.json.
quality and evaluation: silent checklist in references/quality-checklist.md and reusable tests in references/eval-cases.md.

Read the full file on GitHub · 113 lines

Files

What ships with it

16 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.

8d ago First seen · 113 lines · 106 tokens per session scan A 58ccae2eadb3

Subscribe to this mod's changes

one-turn-proposal is a skill published in the GitHub repository theseussss/roamfound (5 stars, last pushed 2mo ago), licensed MIT. It adds 106 tokens to every session and 1,675 once invoked, about $0.0005 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.

Planning Writing and docs

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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens