agentmods.dev

find-solutions

find-solutions is a skill for Claude Code from Refusned/claude-find-solutions. It costs 51 tokens per session (1,398 once invoked), scanned A, original, MIT.

A tool-guided process for finding existing projects and libraries before building a new solution from scratch. It combines broad source searches with GitHub repository results and considers licensing.

In plain words
What is it for?
Use it to search for comparable products or libraries, rank candidate repositories, inspect their popularity and freshness, and produce a reuse-or-rebuild recommendation.
Why use it?
It helps determine whether an idea already exists and whether reusing, rebuilding, or changing direction is the sensible choice.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

not rated 2repo 3mo ago A scan 51 tokens original MIT

Good fit Use it to search for comparable products or libraries, rank candidate repositories, inspect their popularity and freshness, and produce a reuse-or-rebuild recommendation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/refusned/claude-find-solutions/claude-find-solutions
View source ↗ Refusned/claude-find-solutions
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 Refusned/claude-find-solutions --skill claude-find-solutions
Clone the repo
git clone --depth 1 https://github.com/Refusned/claude-find-solutions

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 find-solutions

README.md
[![agentmods](https://agentmods.dev/badge/skills/refusned/claude-find-solutions/claude-find-solutions/github.svg)](https://agentmods.dev/skills/refusned/claude-find-solutions/claude-find-solutions)
Your own site
<a href="https://agentmods.dev/skills/refusned/claude-find-solutions/claude-find-solutions"><img src="https://agentmods.dev/badge/skills/refusned/claude-find-solutions/claude-find-solutions/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 find-solutions

Your own site · 80×15
<a href="https://agentmods.dev/skills/refusned/claude-find-solutions/claude-find-solutions"><img src="https://agentmods.dev/badge/skills/refusned/claude-find-solutions/claude-find-solutions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,398 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 $0.00051 $0.01398
Opus 5 $0.00026 $0.00699
Sonnet 5 $0.00010 $0.00280
Haiku 4.5 $0.00005 $0.00140

Measured 10d ago against content hash 9af6a4cdd957, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

find-solutions 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.

SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/find-solutions — Ready-made solution finder

Compose idea-reality-mcp (multi-source aggregated check) + mcp-omnisearch.github_search (stars-sorted repo search) into one ranked list with a license-aware verdict.

Procedure

  1. Extract the idea. Take the user's text from the skill argument. If empty, ask: "Опиши идею одной фразой — что хочешь сделать?" Stop until answered.

  2. Two parallel tool calls in one message:

    • mcp__idea-reality__idea_check(idea_text, depth="deep") — GitHub + HN + npm + PyPI + Product Hunt + SO with reality_signal + top_similars
    • mcp__mcp-omnisearch__github_search(query=<idea>, search_type="repositories", sort="stars", limit=10) — stars-ranked GitHub repos

  3. Build a unified solutions list. For each item from both sources, capture: {name, url, source, stars_or_count, description, last_updated, license}.

  4. Enrich top 5 GitHub candidates with license + freshness (omnisearch and idea-reality don't return these). Use Bash:

    for repo in <top 5 owner/repo>; do
  gh api repos/$repo --jq "[\"$repo\", .license.spdx_id // \"NOASSERTION\", .stargazers_count, .pushed_at[:10]] | @tsv"
done

    Treat NOASSERTION literally — GitHub couldn't classify the license file, so block confident copy/adapt for that repo even if you "know" it's MIT (per Codex #7 + #18).

  5. Identity-resolve dedup (fixes Codex BLOCKER #5). Normalize all github.com/<owner>/<repo> URLs (strip protocol, trailing slash, .git, case). Merge entries with the same owner/repo into one — prefer the entry with richer metadata (license, stars). Do NOT dedup by raw URL string only.

  6. Apply per-source thresholds (fixes Codex BLOCKERS #1, #2). Do not use cross-ecosystem constants. Per source:

    • GitHub stars: ≥500 = mainstream, ≥5 000 = canonical
    • npm: existence of package + ≥10 packages matching query = saturated market
    • PyPI: treat as binary (exists / not) — idea-reality reports counts, not downloads
    • crates.io: existence + count signal
    • HN mentions: ≥50 in last 12 months = community awareness; trend accelerating ⇒ market moving
    • Use reality_signal from idea-reality only as a sanity check, NOT as the verdict driver.

Read the full file on GitHub · 98 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 · 98 lines · 51 tokens per session scan A 9af6a4cdd957

Subscribe to this mod's changes

find-solutions is a skill published in the GitHub repository Refusned/claude-find-solutions (2 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 1,398 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.

Claude CodeResearchai-agentclaude-code-skilldeveloper-toolsmcpmodel-context-protocol
Related

Other skills, from other repositories

blast-radius

Trace ServiceNow configuration dependencies — what artifacts touch a given field, what calls a script include, table/app-level config inventory. Use before deletes, renames, or refactors.

serac-labs/serac · 39 tokens

change-management

Create and transition ServiceNow change requests (normal/standard/emergency), change tasks, affected CIs, approval routing, CAB scheduling, and conflict detection across maintenance windows.

serac-labs/serac · 37 tokens

cmdb-patterns

Create ServiceNow CIs and cmdbrelci relationships, walk upstream/downstream impact, detect orphan/stale CIs, and align discovered CIs with the proper sysclassname hierarchy.

serac-labs/serac · 43 tokens

csm-patterns

Build ServiceNow Customer Service Management — customeraccount, customercontact, sncustomerservicecase routing, service entitlements with usage decrement, and Customer Portal case submission widgets.

serac-labs/serac · 39 tokens

incident-management

Manage ServiceNow incidents — creation with impact/urgency priority calc, auto-assignment by category, reassignment tracking, major incident declaration with bridge calls, time-based escalation, MTTR metrics.

serac-labs/serac · 42 tokens

client-scripts

Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.

serac-labs/serac · 45 tokens