clarify-goal

clarify-goal is a skill for Claude Code from SebastianElvis/reaper. It costs 62 tokens per session (1,076 once invoked), scanned A, original, Apache-2.0.

A question-setting tool that turns a vague research goal into a precise one by asking targeted questions, with or without a source paper.

In plain words
What is it for?
Use it to clarify which parts of a paper to study, what threat model applies, or what it means for a claim to be broken.
Why use it?
It prevents research from starting with unclear scope, assumptions, or definitions of what would count as a problem.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the reaper plugin — 10 skills shipped together

Good fit Use it to clarify which parts of a paper to study, what threat model applies, or what it means for a claim to be broken.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sebastianelvis/reaper/clarify-goal
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 SebastianElvis/reaper --skill clarify-goal
Clone the repo
git clone --depth 1 https://github.com/SebastianElvis/reaper

Made for: Claude Code.

Or install reaper, the plugin that ships this one along with the rest of its 10 skills.

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 clarify-goal

README.md
[![agentmods](https://agentmods.dev/badge/skills/sebastianelvis/reaper/clarify-goal/github.svg)](https://agentmods.dev/skills/sebastianelvis/reaper/clarify-goal)
Your own site
<a href="https://agentmods.dev/skills/sebastianelvis/reaper/clarify-goal"><img src="https://agentmods.dev/badge/skills/sebastianelvis/reaper/clarify-goal/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 clarify-goal

Your own site · 80×15
<a href="https://agentmods.dev/skills/sebastianelvis/reaper/clarify-goal"><img src="https://agentmods.dev/badge/skills/sebastianelvis/reaper/clarify-goal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,076 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 $0.00062 $0.01076
Opus 5 $0.00031 $0.00538
Sonnet 5 $0.00012 $0.00215
Haiku 4.5 $0.00006 $0.00108

Measured 12d ago against content hash 99073dfbd38c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

clarify-goal 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 12d 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/clarify-goal/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clarify Goal

Ask the user targeted questions to sharpen a vague research goal into something the pipeline can act on precisely.

Usage

Invoke this skill by name with the research goal (and optional paper path). On slash-command hosts, prefix with / (e.g. /clarify-goal "<goal>").

# Without a paper — goal-driven research
clarify-goal "explore the feasibility of post-quantum threshold signatures"

# With a paper
clarify-goal "is this protocol secure?" path/to/paper.pdf

Argument parsing: The research goal (quoted string) is required. If a path to an existing file is also provided, treat it as the paper.

Instructions

1. Read the Paper (quick scan) — if provided

If a paper path was provided: Read the paper at the given path. Do a fast scan — you are not producing a full analysis, just enough to understand:

  • What the paper is about (topic, system, protocol)
  • What it claims (main theorems, security properties, performance results)
  • Its structure (which sections cover what)

If no paper was provided: Skip this step. You will clarify the goal based on the research prompt alone, using your knowledge of the research domain.

2. Identify Ambiguities

Compare the user's research goal against what the paper contains (if provided) or against the research domain in general. Look for:

  • Scope ambiguity: Does the goal apply to a whole paper/field or specific sections/theorems/protocols?
  • Definition ambiguity: Does the goal use terms that could mean multiple things? (e.g., "secure" — against what adversary? under what model?)
  • Success criteria ambiguity: What would a satisfying answer look like? A counterexample? A proof gap? A performance bound?
  • Assumption ambiguity: Are there implicit assumptions the user might want to constrain or relax? (e.g., synchrony vs. asynchrony, static vs. adaptive adversary)
  • Comparison ambiguity: If the goal involves comparison ("is this better than X?"), what metric and what baseline?

Read the full file on GitHub · 103 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. 12d ago First seen · 103 lines · 62 tokens per session scan A 99073dfbd38c

Subscribe to this mod's changes

clarify-goal is a skill published in the GitHub repository SebastianElvis/reaper (9 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,076 once invoked, about $0.0003 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

literature-review-agent

Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by paperId), cross-corroborate against Crossref + OpenAlex to…

Ar9av/PaperOrchestra · 149 tokens

agent-research-aggregator

Pre-pipeline aggregator that scans AI agent cache directories (.claude, .cursor, .antigravity, .openclaw) or any user-specified directory for experimentation logs, extracts insights and numeric results, and formats them as PaperOrchestra-ready inputs (idea.md + experimentallog.md). TRIGGER when the user says…

Ar9av/PaperOrchestra · 177 tokens

content-refinement-agent

Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules, deterministic 0-100 decision bands (Accept/Minor/Major/Reject) that drive a target-met early stop, and a Devil's Advocate…

Ar9av/PaperOrchestra · 145 tokens

paper-orchestra

Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines, optional figures) into a submission-ready LaTeX manuscript and compiled PDF. TRIGGER when the user asks to "write a paper…

Ar9av/PaperOrchestra · 143 tokens

section-writing-agent

Step 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experiments, Conclusion), extracts numeric values from experimentallog.md into LaTeX booktabs tables, splices the generated figures from Step 2, and merges…

Ar9av/PaperOrchestra · 125 tokens

plotting-agent

Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimentallog.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER…

Ar9av/PaperOrchestra · 102 tokens