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.
npx skills add inbharatai/claude-skills --skill source-evaluatorgit clone --depth 1 https://github.com/inbharatai/claude-skillsWrote 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.
[](https://agentmods.dev/skills/inbharatai/claude-skills/source-evaluator)<a href="https://agentmods.dev/skills/inbharatai/claude-skills/source-evaluator"><img src="https://agentmods.dev/badge/skills/inbharatai/claude-skills/source-evaluator/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.
<a href="https://agentmods.dev/skills/inbharatai/claude-skills/source-evaluator"><img src="https://agentmods.dev/badge/skills/inbharatai/claude-skills/source-evaluator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00022 | $0.00386 |
| Opus 5 | $0.00011 | $0.00193 |
| Sonnet 5 | $0.00004 | $0.00077 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
source-evaluator 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 9d 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.
This is a copy
86% identical to proposal-writer — 34 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Source Evaluator
Overview
Evaluate information sources — CRAAP test, lateral reading, domain authority, and bias assessment.
When to Use This Skill
Use Source Evaluator when you need to:
- Work with source evaluator tasks in your project or workflow
- Automate source evaluator operations at scale
- Generate production-quality source evaluator output quickly
Instructions
When this skill is active, Claude will:
- Understand the full context of your source evaluator request
- Apply best practices and conventions for Research & Analysis
- Produce clean, well-structured, production-ready output
- Explain key decisions and offer alternatives where relevant
Examples
Example 1 — Basic Usage
User: Help me get started with source evaluator.
Claude: I'll walk you through the essential steps for source evaluator in your context...
Example 2 — Advanced Usage
User: I need a production-ready source evaluator setup with full error handling.
Claude: Here's a complete, production-hardened source evaluator implementation...
Guidelines
- Always validate inputs before processing
- Follow the conventions of the target platform or language
- Prefer explicit over implicit — clarity beats cleverness
- Include comments for non-obvious logic
- Suggest tests or validation steps where appropriate
Dependencies
Required: none
Platforms
Available on: claude.ai, api
Part of the claude-skills collection — 183+ skills for Claude.
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.
- 9d ago First seen · 68 lines · 22 tokens per session scan A 2be3e0f14101
source-evaluator is a skill published in the GitHub repository inbharatai/claude-skills (33 stars, last pushed 6mo ago), licensed MIT. It adds 22 tokens to every session and 386 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to proposal-writer, differing in 34 lines, and is treated as a copy.
Other skills, from other repositories
human-review
Produce a plain-English review of the files you just edited and gate the changes behind an explicit Approve/Undo choice. Use when the Stop hook from the human-review-skill plugin asks for a review (you'll see a prompt referencing an edit log), OR when the developer's most recent message is "1", "2", "approve", or…
optimize
Automatically refines every user prompt into a structured, actionable version, then immediately executes the optimized prompt. When triggered explicitly with "/optimize {prompt}", "optimize:", or "optimize prompt:", outputs the refined prompt as text instead.
mysql-migration
MySQL schema migration safety reviewer and DDL generator. ALWAYS use when writing, reviewing, or planning MySQL schema changes — ALTER TABLE, CREATE/DROP INDEX, column type changes, charset conversions, data backfills, or any DDL touching production tables. Covers online DDL algorithm selection (INSTANT/INPLACE/COPY)…
redis-cache-strategy
Redis caching strategy designer and reviewer. ALWAYS use when designing, reviewing, or troubleshooting Redis caching layers — cache pattern selection (cache-aside, write-through, write-behind), TTL strategy, cache stampede/penetration/avalanche prevention, hot key handling, cache-DB consistency, distributed locking…
systematic-debugging
Use when debugging, diagnosing, or investigating any bug, test failure, flaky test, race condition, unexpected behavior, build failure, production incident, third-party breakage, root cause analysis, or performance regression before proposing fixes.
google-search
Use when the user wants help finding information through Google or Google-style web search and expects more than raw links. Handle current facts, public-information lookups, official documents, tutorials, reports, tools, materials, or source discovery by classifying the search goal, generating precise queries…