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 ByamB4/find-cve-agent --skill report-writinggit clone --depth 1 https://github.com/ByamB4/find-cve-agentWrote 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/byamb4/find-cve-agent/report-writing)<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.
<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>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 | $0.00036 | $0.02041 |
| Opus 5 | $0.00018 | $0.01020 |
| Sonnet 5 | $0.00007 | $0.00408 |
| Haiku 4.5 | $0.00004 | $0.00204 |
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.
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
/reportcommand 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 |
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.
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 · 188 lines · 36 tokens per session scan A 5b92558cf3c3
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.
Other skills, from other repositories
wordpress-plugin-hunt
Hunt WP plugins via REST, exploit CVEs when version known.
deep-invade
Deep pentest WP: SSRF, plugin CVE, JS mine, port scan chain.
zimbra-attack
Zimbra SOAP user enum, CVE-2022-37042, SSRF when webmail.
wp-plugin-cve-hunt
Systematic approach to finding and testing CVEs for identified WordPress plugins. Covers plugin discovery, version extraction from multiple sources (readme.txt, assets, inline JS), CVE database cross-referencing with WPScan/Patchstack/NVD/NVD API, version-based vulnerability matching, exploitation PoC generation, and…
analyzing-sbom-for-supply-chain-vulnerabilities
Parses Software Bill of Materials (SBOM) in CycloneDX and SPDX JSON formats to identify supply chain vulnerabilities by correlating components against the NVD CVE database via the NVD 2.0 API. Builds dependency graphs, calculates risk scores, identifies transitive vulnerability paths, and generates compliance reports.…
bug-bounty-hunting
Hunt vulnerabilities like an expert, not a linear software engineer: come at a target from the overlooked angle, reason by analogy and transfer proven attack mechanisms, attack the hidden assumptions and the seams between systems, drill to the mechanism, then keep it honest with proof and persistence (acceptance !=…