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 surfmind-space/awesome-surfmind --skill source-findergit clone --depth 1 https://github.com/surfmind-space/awesome-surfmindWrote 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/surfmind-space/awesome-surfmind/source-finder)<a href="https://agentmods.dev/skills/surfmind-space/awesome-surfmind/source-finder"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/source-finder.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.00590 |
| Opus 5 | $0.00043 | $0.00295 |
| Sonnet 5 | $0.00017 | $0.00118 |
| Haiku 4.5 | $0.00009 | $0.00059 |
Grade A, and why
source-finder 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source Finder
Find credible primary or authoritative sources that verify, challenge, or strengthen the claims in the selected or visible text. Never invent sources, URLs, titles, authors, or dates, present a summary or commentary as a primary source, or inflate a weak source into proof.
- Identify the specific claims or questions that need stronger sourcing, and note the numbers, dates, names, or quotes a source would have to match.
- Prefer primary, official, standards-body, academic, legal, regulatory, or original-data sources over summaries and commentary. Use web search or any browser/MCP tool available, and treat each result as evidence to inspect rather than automatic truth.
- Weigh each candidate for authority, recency, specificity, and whether it actually supports the exact claim, not just the general topic. Before citing a source, confirm it exists and says what you think — open the link or search the exact title or DOI — rather than trusting a recalled reference.
- Flag claims that need a source but can't be verified from the available context, and say what kind of source would settle them.
Report each claim with its best source candidates, why each one is stronger, what it actually supports, and any caveats or gaps. Preserve exact names, numbers, links, dates, and currencies, and don't cite a source unless it directly supports the claim.
Example
Source text: "Intermittent fasting boosts metabolism by 14%."
Claim: Intermittent fasting raises metabolic rate by 14%.
Best source candidates: A peer-reviewed metabolic-ward study in a journal such as The American Journal of Clinical Nutrition, or a systematic review of fasting and resting energy expenditure.
Why each is stronger: Both are primary or pooled measured data, not a press summary; the original study reports the actual measurement and the conditions behind a figure like "14%."
What it supports: Whether a metabolic change of that size was measured, in whom, and over what window — the specific 14% figure, not just "fasting affects metabolism."
Caveats or gaps: The visible text gives no citation, sample, or timeframe, so the 14% can't be traced yet. A single small trial wouldn't settle it; a systematic review would carry more weight.
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.
- 8d ago First seen · 35 lines · 86 tokens per session scan A 8f83ce5b9a53
source-finder is a skill published in the GitHub repository surfmind-space/awesome-surfmind (5 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 590 once invoked, about $0.0004 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.
Other skills, from other repositories
cs-master
Expert computer scientist for algorithms, complexity analysis, and distributed systems.
network-devops
Network performance expert for latency optimization, packet analysis, and infrastructure tuning.
quant-finance
Quantitative finance expert for trading strategies, risk management, and portfolio optimization.
uiux-master
UI/UX expert for design systems, accessibility, and avoiding generic AI-generated design patterns.
c-master
C programming expert for memory management, systems programming, and performance optimization.
data-science
ML engineering expert for feature engineering, model debugging, and production pipelines.