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 goperigon/perigon-mcp-server --skill news-researchgit clone --depth 1 https://github.com/goperigon/perigon-mcp-serverWrote 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/goperigon/perigon-mcp-server/news-research)<a href="https://agentmods.dev/skills/goperigon/perigon-mcp-server/news-research"><img src="https://agentmods.dev/badge/skills/goperigon/perigon-mcp-server/news-research/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/goperigon/perigon-mcp-server/news-research"><img src="https://agentmods.dev/badge/skills/goperigon/perigon-mcp-server/news-research.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 | $0.00064 | $0.00903 |
| Opus 5.5 | $0.00026 | $0.00361 |
| Sonnet 5.5 | $0.00013 | $0.00181 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
perigon-news-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 2d 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
100% identical to perigon-news-research — 0 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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this skill for open-web news intelligence through the Perigon MCP server. The server enforces authentication, scopes, and quotas; this skill defines how to combine tools into reliable, cited answers.
Session setup
- Treat today’s date (and the user’s timezone if known) as the anchor for “recent,” “this week,” and “today.” Do not assume the model cutoff is current.
- Call
get_api_accessonce at the start of a research session, and again after any 403 or unexpectedly empty or stripped field. Do not infer missing data as “none exists” until entitlements are checked. - When the host exposes MCP resources, read
perigon://reference/entitlementsafterget_api_accessif behavior is unclear. For multi-step entity work, readperigon://reference/chaining. For field semantics, readperigon://reference/fields.
Core rules
- Resolve names to IDs before filtering when possible (
search_companies→ company id,search_people→ wikidata id,search_sources→ source id). Names collide; IDs do not. - Prefer stats tools over counting search results manually. Pair
get_article_countswithget_avg_sentimentusing identical filters when the user asks about trends. - Cite sources. When reporting facts from articles, include publication, title, date, and URL when the tool returns them. Do not invent articles, quotes, or URLs.
- Do not mutate monitors, watchlists, or source groups unless the user explicitly asks to create, update, or change status.
- If a tool is unavailable in the session, say so and offer what is available under the current scopes—do not silently skip steps.
Workflows
Headlines and discovery
- Clarify geography, topic, and time window if the request is vague.
- Use
search_news_articlesfor article-level results; usesearch_news_storieswhen the user wants clustered narratives (requires clusters scope). - For semantic “find articles like this” requests, use
search_vector_newswhen entitled.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 66 lines · 64 tokens per session scan A 2cc21ea2e6fe
perigon-news-research is a skill published in the GitHub repository goperigon/perigon-mcp-server (6 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 903 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to perigon-news-research, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
research-stocks
Read current stock research, technical backtests, saved analyses or saved backtests. Use for a named ticker or watchlist research history; preserve source dates, model limitations and risk factors.
compare-macro-history
Compare CPI, interest rates and sovereign yield histories from seeded official reports. Use for inflation or rate trends; preserve country provenance, index base, frequency, yield measure and missing readings.
assess-energy-shock
Model oil or gas supply shock exposure for a country and chokepoint. Use when the user asks how an energy disruption could affect fuel supply, strategic cover, or product deficits.
fetch-news-digest
Retrieve the pre-aggregated digest of World Monitor's curated news feeds, bucketed by category, with per-article threat classification and alert flags. Use when the user asks what's in the news right now, wants headlines by topic, or needs a current-events sweep.
track-tariff-trends
Retrieve a country's average applied tariff over time — the MFN rate on all products, or the rate it applies on goods from one partner and/or in one product group — plus the optional US effective tariff rate. Use when the user asks how a country's tariffs have changed, or what it charges another country on average.…
lookup-us-import-duty
Look up the current US import duty on one HTS product from one country — the HTS column rate (MFN, trade-agreement or column 2) plus the Section 301 and 232 duties in chapter 99 — from the live USITC Harmonized Tariff Schedule. Use when the user asks what the US charges today on a product from a specific country…