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 intentic/intentic --skill firecrawlgit clone --depth 1 https://github.com/intentic/intenticWrote 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/intentic/intentic/firecrawl)<a href="https://agentmods.dev/skills/intentic/intentic/firecrawl"><img src="https://agentmods.dev/badge/skills/intentic/intentic/firecrawl/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/intentic/intentic/firecrawl"><img src="https://agentmods.dev/badge/skills/intentic/intentic/firecrawl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 12 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00052 | $0.00965 |
| Opus 5.5 | $0.00021 | $0.00386 |
| Sonnet 5.5 | $0.00010 | $0.00193 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
firecrawl scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
fc() { curl -s -X POST -H "Authorization: Bearer $FIRECRAWL_API_KEY" -H "Content-Type: application/json" \ How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Firecrawl (connected)
Key in $FIRECRAWL_API_KEY, base in $FIRECRAWL_API_URL (https://api.firecrawl.dev unless self-hosted).
Everything is POST /v2/<endpoint> with a JSON body. Define this helper once per shell: fc <path> '<json>':
fc() { curl -s -X POST -H "Authorization: Bearer $FIRECRAWL_API_KEY" -H "Content-Type: application/json" \
-d "$2" "$FIRECRAWL_API_URL/v2/$1"; }
Responses are {success, data} (or {success:false, error}: read error, it says what was wrong). This is
metered: one page ≈ one credit. Prefer scrape on a known URL and map to find one; reach for crawl only
when whole-site content is genuinely wanted, and always pass limit.
- Scrape one page:
fc scrape '{"url":"<URL>","formats":["markdown"]}' | jq -r '.data.markdown',.data.metadatacarries{title, description, sourceURL, statusCode} - Keep the page's own boilerplate out (default) or bring it back:
"onlyMainContent": false. For a JS-heavy page add"waitFor": 3000 - Just the links / a summary:
"formats":["links"]→.data.links·"formats":["summary"]→.data.summary - Structured fields out of a page:
fc scrape '{"url":"<URL>","formats":[{"type":"json","prompt":"the price and the release date","schema":{"type":"object","properties":{"price":{"type":"string"},"released":{"type":"string"}}}}]}' | jq '.data.json' - Map a site's URLs, cheap, and the right first move on an unfamiliar site:
fc map '{"url":"<URL>","limit":100}' | jq -r '.links[] | .url'(add"search":"<TERM>"to order by relevance) - Search the web:
fc search '{"query":"<QUERY>","limit":5}' | jq -c '.data.web[] | {title, url, description}', add"scrapeOptions":{"formats":["markdown"]}to get each hit's text in the same call, and narrow with"includeDomains":["example.com"],"categories":[{"type":"research"}]or"tbs":"qdr:w"(past week) - Several known URLs at once:
fc batch/scrape '{"urls":["<URL1>","<URL2>"],"formats":["markdown"]}', async, polls like a crawl below
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.
- 1mo ago First seen · 45 lines · 52 tokens per session scan A 103e2b5e7bd7
firecrawl is a skill published in the GitHub repository intentic/intentic (85 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 965 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other skills, from other repositories
modernize-tests
Modernize test suites to use modern Swift Testing features or migrate from XCTest.
device-interaction
Verify iOS app behavior on device or simulator via screenshots, UI hierarchy, and touch interactions.
apple-context
Use calendar and location modules for user-approved Apple Calendar events and current device location.
image-vision
Inspect attached or local images and visually analyze PDFs with vision. Use for photos, screenshots, scans, charts, diagrams, OCR, handwriting, UI inspection, or any task that depends on pixels, layout, or other non-structural page content.
audit-xcode-security-settings
Audit and enable security-oriented Xcode build settings. Progressively enables compiler warnings, static analyzer checkers, and Enhanced Security features. Use when: user wants to secure their Xcode project, audit security settings, enable hardening, review security posture of build configuration, set up…
uikit-app-modernization
Modernizes UIKit apps for multi-window environments by replacing legacy shared-state APIs with context-appropriate modern alternatives. This includes references to mainScreen, interfaceOrientation, application and scene lifecycle, as well as safe area inset updates.