skill_hunter

A skill-selection guide that checks whether an existing reusable tool or workflow fits a requested task before implementation begins.

In plain words
What is it for?
Use it before writing, building, converting, testing, documenting, or automating something to decide whether to reuse, adapt, or create a solution.
Why use it?
It reduces duplicated work and helps keep changes within scope. It also identifies risks, approval needs, and the smallest useful verification step.

Skill for Claude CodeCodex

Part of the skill-hunter plugin — 1 skill, 1 hook shipped together

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/mturac/skill-hunter/skill_hunter
Any agent
npx skills add mturac/skill-hunter --skill skill_hunter
Clone the repo
git clone --depth 1 https://github.com/mturac/skill-hunter

Made for: Claude Code, Codex.

Or install skill-hunter, the plugin that ships this one along with the rest of its 1 skill, 1 hook.

Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 882 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 $0.00131 $0.00882
Opus 5 $0.00066 $0.00441
Sonnet 5 $0.00026 $0.00176
Haiku 4.5 $0.00013 $0.00088

Measured 3d ago against content hash 33a0ff09fda1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill_hunter 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 3d 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/skill_hunter/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Hunter

Your job is not to immediately execute the user's request. Your first responsibility is to decide whether an existing reusable solution can solve or accelerate it.

Precedence

Safety and privacy rules outrank convenience. If instructions conflict, choose the safer path or ask for clarification. Never weaken approval, credential, or destructive-action gates silently.

Responsibility Contract

Role: accountable Skill Hunter scout and execution advisor. Owned surface: only the requested task, files, module, workflow, or documentation. Constraints and non-goals: preserve existing behavior and avoid unrelated changes. Acceptance: the user sees a clear reuse decision before implementation. Verification: use the smallest relevant test, audit, or syntax check. Final report: changed files, verification results, and residual risk.

Tool Contract

Treat tools as candidates until the host exposes a callable schema. Required decision schema fields: goal, decision, candidates_checked, recommended_path, risk, approval_required, and next_action. Decision enum: USE_EXISTING, ADAPT_EXISTING, BUILD_MINIMAL, BUILD_CUSTOM, ASK_USER, AVOID.

Recommendation Context

Before recommending, account for location or market, budget, preference or use case, date or timing, constraint, runtime, privacy, credential scope, license, and deployment environment. Missing decision context maps to ASK_USER or an explicit safe default.

Core Rule

Before implementing from scratch, ask: "Is there likely an existing skill/tool/workflow that can solve or accelerate this task?"

If yes, search or reason about candidates, evaluate them, and present the best option before execution.

Skill Discovery Pass

Run when the task involves file conversion, document generation, browser automation, data extraction, scraping, testing, deployment, CI/CD, media generation, design-to-code, API integration, migration, docs generation, scaffolding, database analysis, cloud setup, LLM orchestration, or agent workflows.

Read the full file on GitHub · 77 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. 3d ago First seen · 77 lines · 131 tokens per session scan A 33a0ff09fda1

Subscribe to this mod's changes

skill_hunter is a skill published in the GitHub repository mturac/skill-hunter (2 stars, last pushed 3mo ago), licensed MIT. It adds 131 tokens to every session and 882 once invoked, about $0.0007 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

find-skills

Discovers, searches, and installs skills from multiple AI agent skill marketplaces (400K+ skills) using the SkillKit CLI. Supports browsing official partner collections (Anthropic, Vercel, Supabase, Stripe, and more) and community repositories, searching by domain or technology, and installing specific skills from…

rohitg00/skillkit · 162 tokens

janitor-discover

Find new skills on GitHub or check a specific skill before installing. Use when the user wants to search for skills, evaluate a skill URL, check overlap and security risk before installing, or compare a local skill against alternatives. Trigger with '/janitor-discover'.

khendzel/skills-janitor · 58 tokens

find-skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. Uses reskill as the package manager.

kanyun-inc/reskill · 54 tokens

llms-txt-aware

Antes de fetchear, scrapear o llamar cualquier endpoint de un dominio web, buscá su archivo /llms.txt y, si existe, leelo COMPLETO (no solo la sección ## Skills). Usalo como manual operativo del sitio: endpoints, parámetros, límites, ejemplos canónicos, notas para agentes y skills publicadas. Activá esta skill en…

MauricioPerera/llms-txt-skills · 127 tokens

placeholder

Generate SVG placeholder images for UI mockups via the placeholder-img HTTP API. Use when the user asks for placeholder images, mockup assets, or dummy images with specific dimensions and colors.

MauricioPerera/llms-txt-skills · 39 tokens

api-client

Patterns for consuming the img.automators.work placeholder image API via HTTP. Use when building HTML mockups, CSS backgrounds, or design prototypes that need SVG placeholder images of specific dimensions and colors.

MauricioPerera/llms-txt-skills · 42 tokens