keel-research

keel-research is a skill for Claude Code from muratsilahtaroglu/claude-code-starter-kit. It costs 31 tokens per session (328 once invoked), scanned A, original, MIT.

An optional workflow for researching GitHub, articles, LinkedIn, Hugging Face, and other web sources. It saves findings with source links and confidence notes.

In plain words
What is it for?
Use it for approved external research, source checking, platform-by-platform investigation, and summaries that support project decisions.
Why use it?
It creates a traceable evidence record instead of relying on search snippets or unsupported claims.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions subagents.

Good fit Use it for approved external research, source checking, platform-by-platform investigation, and summaries that support project decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/muratsilahtaroglu/claude-code-starter-kit/keel-research
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 muratsilahtaroglu/claude-code-starter-kit --skill keel-research
Clone the repo
git clone --depth 1 https://github.com/muratsilahtaroglu/claude-code-starter-kit

Made for: Claude Code.

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 keel-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/muratsilahtaroglu/claude-code-starter-kit/keel-research.svg)](https://agentmods.dev/skills/muratsilahtaroglu/claude-code-starter-kit/keel-research)
Your own site
<a href="https://agentmods.dev/skills/muratsilahtaroglu/claude-code-starter-kit/keel-research"><img src="https://agentmods.dev/badge/skills/muratsilahtaroglu/claude-code-starter-kit/keel-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 328 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 $0.00031 $0.00328
Opus 5 $0.00015 $0.00164
Sonnet 5 $0.00006 $0.00066
Haiku 4.5 $0.00003 $0.00033

Measured 7d ago against content hash 6569c29fd179, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

keel-research 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 7d 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.

.claude/skills/keel-research/SKILL.md · 22 lines

What it actually says

/keel-research — structured, opt-in external research

HARD GATE: never run without the user's explicit opt-in in THIS session (rules.md §8.27). If the user hasn't opted in, stop and ask first. Produce a verified, cited evidence trail — never blind copy.

Workflow:

  1. Scope — confirm the question + which platforms to scan (github, articles, linkedin, huggingface, web). Add/drop platforms to fit the question.
  2. Fan out — one researcher subagent (.claude/agents/researcher.md) per platform, in parallel. Each searches, reads real sources (not just snippets), and writes research/<platform>/findings.md. Large/raw artifacts go to research/<platform>/downloads/ (git-ignored).
  3. Cite + rate — every claim carries its source URL + a confidence note; flag low-signal/paywalled sources.
  4. Verify (rules.md §4) — as the main agent, don't accept sub-agent output blindly; sanity-check the load-bearing claims before they drive anything.
  5. Synthesize — a short cross-platform summary; conclusions that drive a decision go into an ADR (docs/adr/) or docs/, not left buried under research/.
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. 7d ago First seen · 22 lines · 31 tokens per session scan A 6569c29fd179

Subscribe to this mod's changes

keel-research is a skill published in the GitHub repository muratsilahtaroglu/claude-code-starter-kit (9 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 328 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 2026-08-31.

Related

Other skills, from other repositories

agent-carnet

Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.

yamadashy/repomix · 67 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

security-audit

Audit a codebase or directory for security issues (hardcoded secrets, injection, unsafe deserialization, weak crypto, authz gaps) and produce a structured findings report. Use when the user asks for a security review, an audit, or to check code for vulnerabilities. Report only — never fix.

omnigent-ai/omnigent · 64 tokens

taiyi-ui-design

A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.

Dong90/oh-my-taiyiforge · 35 tokens

taiyi-evolve

A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.

Dong90/oh-my-taiyiforge · 37 tokens

taiyi-diagram-c4

A code-scanning tool that builds C4 architecture documents from a repository. It separates facts observed in the code from conclusions inferred about the design and uses Mermaid diagrams as the source format.

Dong90/oh-my-taiyiforge · 48 tokens