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 lossless-group/lossless-agent-skills --skill crawl-fetch-ingestgit clone --depth 1 https://github.com/lossless-group/lossless-agent-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/lossless-group/lossless-agent-skills/crawl-fetch-ingest)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/crawl-fetch-ingest"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/crawl-fetch-ingest/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/lossless-group/lossless-agent-skills/crawl-fetch-ingest"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/crawl-fetch-ingest.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 | $0.00313 | $0.06728 |
| Opus 5 | $0.00156 | $0.03364 |
| Sonnet 5 | $0.00063 | $0.01346 |
| Haiku 4.5 | $0.00031 | $0.00673 |
Grade A, and why
crawl-fetch-ingest 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 11d 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.
| **Bash + curl** | built-in | Downloading assets to disk | After you've resolved the asset URL. | How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crawl, Fetch, Ingest
Given a deck PDF and/or a firm URL, fill in the team and portfolio metadata so a designer can drop it into HTML/Tailwind/Reveal slides without hand-collecting every headshot, title, and logo.
When to use this skill
- Recreating a VC firm's team / advisor / portfolio sections for a redesigned deck or web presentation
- Filling team metadata for an investment memo, fund one-pager, or fundraise deck
- Asset hunt: SVG logos, favicons, headshots, LinkedIn URLs for people who appear in a PDF or on a firm's site
- Any "here's a PDF, give me a clean dataset of who's in it" task at the org/portfolio level
- Any 2nd / 3rd-order crawl: VC firm → portfolio companies → those companies' CEOs
- Credibility ingest for an operating company's fundraise — walk outward through its backers to make those firms legible to readers starting from near-zero context
Anchor types — two starting points, same cascade
The skill supports two starting anchors. Both are first-class. They share the same fetch cascade (Jina / Firecrawl / OpenGraph.io / Brandfetch / SVG-tier fallback / bg-strip) and the same schema. Only the entry point and stop condition differ.
Anchor: VC firm Anchor: Operating company
→ team → list of backer firms
→ portfolio cos → for each backer:
→ portco CEOs → team
→ portfolio cos
(stop — no portco CEOs)
Firm-anchored (the original walk): one VC firm is the root. Used when you're rebuilding a firm's own deck, memo, or website. See ## The four checkpoints below.
Company-anchored (credibility-card walk): one operating company is the root, and we walk outward through its named backers. Used when an operating company's deck/site needs to make its investor list legible to readers who don't know those firms. The traversal stops at the backers' portfolio companies — portco CEOs add no legibility at credibility-card distance. See routines/investor-credibility-ingest.md.
What ships with it
16 files 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.
- examples/example-firm.md 943 B
- future-work.md 5.0 KB
- routines/investor-credibility-ingest.md 8.6 KB
- routines/triage-brand-assets.md 6.9 KB
- schema/company.md 8.4 KB
- schema/firm.md 2.3 KB
- schema/person.md 6.8 KB
- scripts/bg-strip.sh 5.2 KB runs code
- scripts/brandfetch.ts 15 KB runs code
- scripts/favicon-hunt.sh 7.5 KB runs code
- scripts/jina-reader.ts 2.8 KB runs code
- scripts/logo-hunt.sh 5.7 KB runs code
- scripts/og-fetch.ts 2.8 KB runs code
- scripts/og-image-hunt.sh 3.0 KB runs code
- scripts/triage-classify.py 14 KB runs code
- setup.md 4.3 KB
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.
- 11d ago First seen · 310 lines · 313 tokens per session scan A 9702063b9a55
crawl-fetch-ingest is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 18d ago), licensed MIT. It adds 313 tokens to every session and 6,728 once invoked, about $0.0016 per session on Opus 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 2026-08-31.
Other skills, from other repositories
session-review
End-of-session adversarial review loop. Assemble the session's work into a role-assigned, self-contained brief, then run independent reviewers in parallel — an isolated code-reader (the idea-validator agent) that reads the ACTUAL files and web-checks technology currency, plus an external-family model if you have one …
memory-audit
Audit MEMORY.md against the memory discipline — oversized sections, settled multi-session patterns that belong in knowledge/concepts/, stacked chronicle blocks, stale entries. Produces a move plan as a table for approval, then executes the approved moves atomically. Use when the SessionStart hook reports a tripped…
second-opinion
Cross-check the agent's own answer with independent reviewers before bringing it to the user. Use when the user says 'second opinion', 'sanity check', 'cross-check', 'am I missing something', 'stress-test', 'devil's advocate', 'run a full review', 'this is important', 'high-stakes', 'help me choose between', 'critique…
close-session
An end-of-session workflow that reviews new lessons, asks before promoting repeated patterns, refreshes memory files, and writes a handoff.
next-cache-components
Next.js 16 Cache Components guidance. Use when refactoring React Server Components for performance, debugging Partial Prerendering (PPR) issues, or applying the use cache directive, cacheLife, cacheTag, updateTag, and revalidateTag. Also use when deciding whether data should be static, cached, or dynamic, or when…
agents-sdk
Build AI agents on Cloudflare Workers using the Agents SDK or build Model Context Protocol (MCP) servers. Load when creating stateful agents, durable workflows, MCP servers, checking MCP schema/error responses, or reviewing MCP code quality. Covers Agent class, state management, callable RPC, Workflows integration…