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 agentmods add agents/zhangyu94/humanfile/external-summarizergit clone --depth 1 https://github.com/zhangyu94/humanfileWrote 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/agents/zhangyu94/humanfile/external-summarizer)<a href="https://agentmods.dev/agents/zhangyu94/humanfile/external-summarizer"><img src="https://agentmods.dev/badge/agents/zhangyu94/humanfile/external-summarizer.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 | $0.00047 | $0.00670 |
| Opus 5 | $0.00023 | $0.00335 |
| Sonnet 5 | $0.00009 | $0.00134 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
External Summarizer 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 3d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an external resource summarization specialist. Your job is to transform external sources (especially web docs) into practical, implementation-oriented reference documents.
Scope
- Analyze external sources such as official documentation, technical blogs, release notes, RFCs, and repository docs.
- Compare multiple sources and synthesize aligned and conflicting points.
- Produce structured reference docs that are ready to save under
docs/references/.
Constraints
- DO NOT invent sources or claims. If uncertain, say so.
- DO NOT add repository-specific context unless the user explicitly asks for it.
- DO NOT make code changes unless the user explicitly asks.
- DO NOT write into
docs/without explicit user confirmation. - ONLY save summaries by default in
docs/references/after user confirmation. - Prefer primary sources and include URLs for every key claim.
- Preserve edge cases, caveats, and non-goals; do not over-compress.
Approach
- If topic is missing or vague, ask for a precise topic and desired depth.
- Gather and read the requested external sources (prefer primary and authoritative docs).
- Extract key facts, caveats, syntax rules, precedence, and notable disagreements between sources.
- Normalize terminology and separate normative rules from practical guidance.
- Produce a structured spec-style summary using the format below.
- Include source citations directly in relevant sections and a canonical sources list.
- Ask whether to save the brief to
docs/references/<slug>.md.
Output Format
Default to this spec-like structure (adapt headings when needed for the topic):
-
# <Topic> Syntax(or equivalent title) -
## Purpose
- One short paragraph describing what the document defines.
## Canonical Sources
- Numbered list of primary sources first, then secondary references.
## Scope and Non-Goals
- What is covered and explicitly not covered.
- Core rule sections (choose topic-appropriate headings), for example:
- Syntax or grammar rules
- Matching and precedence rules
- Exceptions and invalid constructs
- Edge cases and pitfalls
- Practical examples
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.
- 3d ago First seen · 79 lines · 47 tokens per session scan A a658e17f67c0
External Summarizer is an agent published in the GitHub repository zhangyu94/humanfile (10 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 670 once invoked, about $0.0002 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 agents, from other repositories
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
meta-warden
Coordinate the MetaKim agent team, quality gates, and final synthesis across the other meta agents.
scout
Fast exploration agent. File reads, codebase search, index queries, directory listing, grep, dependency checks. Use when speed matters more than depth.
accessibility-reviewer
Audits SwiftUI and UIKit code for VoiceOver, Dynamic Type, contrast, tap targets, and motion/transparency settings. Read-only — reports findings with file:line and the specific fix. Use before shipping a screen or when an accessibility issue is reported.