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 skills/hoavdc/codexkit/codexkit-document-summarizernpx skills add hoavdc/CodexKit --skill codexkit-document-summarizergit clone --depth 1 https://github.com/hoavdc/CodexKitWhat 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 | $0.00050 | $0.00838 |
| Opus 5 | $0.00025 | $0.00419 |
| Sonnet 5 | $0.00010 | $0.00168 |
| Haiku 4.5 | $0.00005 | $0.00084 |
Grade A, and why
codexkit-document-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 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Summarizer
When to Use
- Summarizing long documents that are not formal business reports.
- Extracting key points from policies, proposals, PDFs, research notes, or document packets.
- Preparing a quick readout before deciding whether to read the full document.
- Comparing multiple documents for themes, contradictions, or action items.
Procedure
Step 1 - Identify Document Type
Classify the source: policy, proposal, memo, research, contract-like document, transcript, academic paper, operating document, or mixed packet.
Step 2 - Extract Core Content
Capture:
- purpose
- main claims or findings
- dates, parties, obligations, or deadlines
- decisions requested
- open questions
- risks or caveats
Step 3 - Separate Summary From Interpretation
Keep source-backed summary separate from analysis or recommendation. Mark anything inferred.
Step 4 - Produce Audience-Specific Output
Adapt format for executive, manager, student, legal/compliance reviewer, or team member.
Step 5 - Add Reading Guidance
State which sections deserve human review and why.
Inputs
| Input | Required | Format |
|---|---|---|
| Document text or excerpt | Yes | Pasted text, extracted notes, OCR |
| Document type | Recommended | Proposal, policy, memo, research, etc. |
| Audience | Recommended | Executive, manager, student, team |
| Desired length | Optional | 5 bullets, one page, detailed brief |
| Focus area | Optional | Risks, obligations, actions, decisions |
Output
## Document Summary - [Document Name]
### One-Line Takeaway
[Core point]
### Key Points
- [Point backed by source]
### Actions / Decisions
| Item | Owner | Deadline | Source Note |
|------|-------|----------|-------------|
### Risks / Caveats
- [Risk]
### Needs Human Review
- [Section or issue]
Quality Criteria
- The summary stays faithful to the document and does not invent missing facts.
- Important dates, obligations, numbers, and decisions are preserved.
- Source-backed summary is separated from interpretation.
- The output states what was not reviewed or could not be verified.
- High-risk documents are flagged for expert review.
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 · 116 lines · 50 tokens per session scan A 1bc2f5aecd13
codexkit-document-summarizer is a skill published in the GitHub repository hoavdc/CodexKit (21 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 838 once invoked, about $0.0003 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.
Other skills, from other repositories
claude_code_delegation
Delegate coding, review, and refactor tasks to Claude Code CLI through Row-Bot's approval-gated shell workflow.
developer_review
Code-review workflow for Developer Studio repositories.
reducing-aigc-detection
Systematically reduce AIGC detection rates in academic papers (Chinese/English). Analyzes detection reports, identifies high-impact sections, applies multi-layer rewriting strategies preserving formatting/footnotes, and verifies results. Supports 维普/知网/Turnitin platforms.
defending-applications
Application security defense knowledge for builders. Covers Web/API/GraphQL hardening (XSS/SQLi/SSRF/IDOR/BOLA/Mass Assignment/deserialization/upload/path traversal), authentication/authorization (OAuth 2.0/OIDC/JWT/Session/Cookie/SAML/SSO), and LLM application security (prompt injection, jailbreak, RAG poisoning…
analyzing-security
Scans code for security vulnerabilities, detects dangerous patterns, and ensures security decisions are documented. Use when running security scans, auditing code, or checking for OWASP issues, injection risks, or sensitive data leaks. Automatically triggered on new modules, security-related changes, or post-refactor.
architecting-security
安全架构与治理：威胁建模 (STRIDE/PASTA/LINDDUN)、零信任身份架构、IAM/SSO/MFA/PAM、合规框架 (SOC2/PCI/HIPAA/GDPR)、DLP、隐私工程、安全控制设计。Use when designing security architecture, threat modeling new systems, implementing zero-trust identity, designing IAM/SSO/PAM, building compliance evidence chains, or planning privacy-by-design.