report-writing

report-writing is a skill for Claude Code from ByamB4/find-cve-agent. It costs 36 tokens per session (2,041 once invoked), scanned A, original, Apache-2.0.

A writing aid for vulnerability disclosure reports, which explain security bugs to software maintainers through channels such as GitHub Security Advisories (GHSA), HackerOne, or email.

In plain words
What is it for?
Use it to draft new vulnerability reports, maintainer follow-ups, and clarifications after a security issue has been confirmed.
Why use it?
It turns a confirmed security finding into a clear report suited to the chosen submission channel, including a CVSS severity score and an appropriate tone.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions Claude Code.

Part of the find-cve-agent plugin — 21 skills, 7 commands, 5 agents shipped together

Good fit Use it to draft new vulnerability reports, maintainer follow-ups, and clarifications after a security issue has been confirmed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/byamb4/find-cve-agent/report-writing
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 ByamB4/find-cve-agent --skill report-writing
Clone the repo
git clone --depth 1 https://github.com/ByamB4/find-cve-agent

Made for: Claude Code.

Or install find-cve-agent, the plugin that ships this one along with the rest of its 21 skills, 7 commands, 5 agents.

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 report-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/byamb4/find-cve-agent/report-writing/github.svg)](https://agentmods.dev/skills/byamb4/find-cve-agent/report-writing)
Your own site
<a href="https://agentmods.dev/skills/byamb4/find-cve-agent/report-writing"><img src="https://agentmods.dev/badge/skills/byamb4/find-cve-agent/report-writing/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 report-writing

Your own site · 80×15
<a href="https://agentmods.dev/skills/byamb4/find-cve-agent/report-writing"><img src="https://agentmods.dev/badge/skills/byamb4/find-cve-agent/report-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,041 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.
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 $0.00036 $0.02041
Opus 5 $0.00018 $0.01020
Sonnet 5 $0.00007 $0.00408
Haiku 4.5 $0.00004 $0.00204

Measured 11d ago against content hash 5b92558cf3c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

report-writing 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 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.

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/report-writing/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Report Writing — Professional Vulnerability Disclosure

When to Use

  • /report command invoked
  • Validator has issued a CONFIRMED verdict
  • Director decides to submit a finding
  • Need to draft a follow-up or clarification to a maintainer

Writing Principles

Sound Human, Not AI

Reports go to real maintainers. They can spot AI-generated text instantly and will take your report less seriously.

Avoid:

  • Starting sentences with "It is worth noting that..." or "It should be noted..."
  • "This vulnerability allows an attacker to..." (every single sentence)
  • Bullet-point-only reports with no narrative flow
  • Overly formal language ("hereby", "aforementioned", "thus")
  • Repeating the same sentence structure back to back
  • Hedging everything ("potentially", "could possibly", "might theoretically")
  • Filler phrases ("in order to", "it is important to", "as a matter of fact")
  • Numbered lists for everything — use prose where it reads better

Do:

  • Write like a competent engineer explaining a bug to a colleague
  • Vary sentence length — mix short punchy sentences with longer explanations
  • Use active voice: "The parser accepts..." not "It can be observed that the parser..."
  • Be direct about impact: "This crashes the process" not "This may potentially lead to a denial of service condition"
  • Use contractions naturally: "doesn't", "won't", "can't" — especially in emails
  • Start paragraphs differently — not every paragraph should begin the same way
  • Include one specific detail that shows you actually tested it (Node version, OS, exact error message)

Tone by Channel

Channel Tone Length Format
GHSA Professional, structured Medium (300-500 words) Markdown with headers
HackerOne Concise, impact-focused Short-medium (200-400 words) Their template format
Email (first contact) Friendly, brief Short (100-150 words) Plain text, no attachments
Email (full report) Professional, thorough Medium (300-500 words) Plain text or markdown
Follow-up / clarification Conversational, helpful Short (50-150 words) Plain text

Read the full file on GitHub · 188 lines

Files

What ships with it

2 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.

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. 11d ago First seen · 188 lines · 36 tokens per session scan A 5b92558cf3c3

Subscribe to this mod's changes

report-writing is a skill published in the GitHub repository ByamB4/find-cve-agent (48 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 2,041 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 2026-08-30.

Related

Other skills, from other repositories