prime-fetch

prime-fetch is a skill for Claude Code from allemaar/open-skills. It costs 102 tokens per session (1,913 once invoked), scanned A, original, Apache-2.0.

A helper that runs a noisy search or file-fetching operation in a separate worker and returns only a checked summary. Grep searches text, Glob finds files, and web or MCP searches retrieve outside information.

In plain words
What is it for?
Use it to search a codebase, find files, fetch web content, or query connected data sources while receiving a filtered digest with proof.
Why use it?
It keeps large, low-value search results out of your main conversation and requires evidence for reported findings. This makes it easier to work with searches that produce lots of irrelevant output.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the open-skills plugin — 70 skills shipped together

Good fit Use it to search a codebase, find files, fetch web content, or query connected data sources while receiving a filtered digest with proof.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/allemaar/open-skills/prime-fetch
Install

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.

Any agent
npx skills add allemaar/open-skills --skill prime-fetch
Clone the repo
git clone --depth 1 https://github.com/allemaar/open-skills

Made for: Claude Code.

Or install open-skills, the plugin that ships this one along with the rest of its 70 skills.

Wrote 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.

agentmods badge for prime-fetch

README.md
[![agentmods](https://agentmods.dev/badge/skills/allemaar/open-skills/prime-fetch/github.svg)](https://agentmods.dev/skills/allemaar/open-skills/prime-fetch)
Your own site
<a href="https://agentmods.dev/skills/allemaar/open-skills/prime-fetch"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/prime-fetch/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.

agentmods 80×15 button for prime-fetch

Your own site · 80×15
<a href="https://agentmods.dev/skills/allemaar/open-skills/prime-fetch"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/prime-fetch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,913 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00102 $0.01913
Opus 5 $0.00051 $0.00957
Sonnet 5 $0.00020 $0.00383
Haiku 4.5 $0.00010 $0.00191

Measured 12d ago against content hash ebcb05c11436, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prime-fetch 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 12d 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.

skills/prime-fetch/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prime-fetch

Wrap a noisy data-fetching tool call in a delegated sub-agent so the raw dump lands in the sub-agent's context, not yours. The lead receives only the filtered, proof-of-work-verified digest.

Structured execution spec: protocol.yon. Read it for the canonical rules and step sequence; this file is explanation. The two must stay in sync — if you edit one, update the other and refresh the @STAMP date.

Caller Options. Before executing, run the Caller Options protocol (caller-options/SKILL.md).

Family invariant — /prime-* skills delegate. Every /prime-* skill uses sub-agents to keep the caller's context clean. /prime-fetch and /prime-sweep additionally require proof-of-work on every finding (source:line + verbatim quote ≥8 words OR a verbatim-token). /prime-expand is exempt — it produces intent (a question + candidate sources), not factual findings.

What's a verbatim-token? A discrete identifier where ≥8 prose words isn't applicable. Examples: version strings (v1.2.3), commit hashes (abc123def), function/class names (MyClass.handleRequest), numeric values (port 8080), enum values (STATUS_PENDING). Must be quoted exactly; the lead still grep-verifies findability.

Boundary

Use /prime-fetch for one read-only data-fetching tool call (Grep, Glob, Read, WebFetch, or an MCP search) regardless of expected result size — the family invariant is about keeping noise out of your context, not about whether the result happens to be small. Do NOT use it for write-side calls (Edit, Write, Bash with side effects), multi-source investigation (use /prime-sweep — threshold ≥3 distinct sources OR ≥~10k tokens), or vague gaps that need articulating first (use /prime-expand). Do NOT use it to gather facts for the user — that is /investigate.

Step 1 — Receive the tool call spec + objective

Inputs:

  • Tool call spec — the call you would run, with all parameters. Examples: Grep(pattern='session', type='ts'), WebFetch(url='https://...'), mcp__claude_ai_Google_Drive__search_files(query='...').
  • Objective — what you are looking for in the result (typically from /prime-expand).

Read the full file on GitHub · 125 lines

Files

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.

Changes

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.

  1. 12d ago First seen · 125 lines · 102 tokens per session scan A ebcb05c11436

Subscribe to this mod's changes

prime-fetch is a skill published in the GitHub repository allemaar/open-skills (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 102 tokens to every session and 1,913 once invoked, about $0.0005 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 2026-08-30.