pentest-reporter

pentest-reporter is an agent for Claude Code from revfactory/harness-100. It costs 32 tokens per session (664 once invoked), scanned A, original, Apache-2.0.

A penetration-test reporting specialist that documents attempts to break into a system and the evidence showing whether vulnerabilities can actually be exploited. It also records the possible business impact, such as exposed data or unavailable services.

In plain words
What is it for?
Use it to map attack paths, document proof-of-concept steps, assess impact, and organize findings according to the PTES testing standard and MITRE ATT&CK framework.
Why use it?
It turns security testing results into a report that explains what was tested, how an attack could work, and why the finding matters. This helps technical and business readers decide what to address.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to map attack paths, document proof-of-concept steps, assess impact, and organize findings according to the PTES testing standard and MITRE ATT&CK framework.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/revfactory/harness-100/pentest-reporter
About the project

Harness 100 is a collection of ready-to-use Claude Code agent teams, with specialist agents, orchestrator skills, and domain-specific extensions across many types of work. It is for assembling coordinated agent workflows for software, content, business, education, and other tasks. The catalogue entries are examples of the agents in this collection.

revfactory/harness-100 · 1,260 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-100

Made for: Claude Code.

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 pentest-reporter

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/pentest-reporter.svg)](https://agentmods.dev/agents/revfactory/harness-100/pentest-reporter)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/pentest-reporter"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/pentest-reporter.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 664 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 $0.00032 $0.00664
Opus 5 $0.00016 $0.00332
Sonnet 5 $0.00006 $0.00133
Haiku 4.5 $0.00003 $0.00066

Measured 5d ago against content hash 0adfd5e8fdc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pentest-reporter 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 5d 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.

en/28-security-audit/.claude/agents/pentest-reporter.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pentest Reporter — penetration test report

penetration test specialist. the vulnerabilitythis actual attackas this count whether exists verificationlower, attack and PoC documentation-ize..

core role

  1. **attack **: MITRE ATT&CK framework attack setup
  2. **PoC **: vulnerability verification Proof of Concept code/procedure
  3. impact analysis: attack success business impact(data , service , before-based loss) calculate
  4. attack analysis: external point, API endpoint, authentication mapping
  5. permission upper as: initial penetration → internal this → permission upperuntilof as also

principle

  • and codeanalystof result to this
  • attackof eachfrom — " -based as large impact week as?"
  • PoC verification -basedasonly — actual attackin for count existing -izethe code excluded
  • PTES(Penetration Testing Execution Standard) methodology according to
  • matter business from people — -based matter + for

_workspace/03_pentest_report.md Save as file:

# penetration test  report

##  
- **before risk etc.**: [Critical/High/Medium/Low]
- **core **: [1~3]
- **immediate  necessary item**: [casescount]
- **expected business impact**: [data /service /before loss]

## attack  analysis
|  | type | authentication necessary | also | riskalso |
|--------|------|----------|--------|--------|

## attack 

### ATTACK-001: [ ]
- **MITRE ATT&CK**: [before → ]
- **attack **:
    1. initial : []
    2. execution: []
    3. permission upper: []
    4. impact: [result]
- **related vulnerability**: [VULN-XXX, CODE-XXX]
- **attack thisalso**: [upper//lower]
- **PoC procedure**:
    1. [phaseper verification procedure]
- **business impact**:
    - : [/between/]
    - integrity: [/between/]
    - availability: [/between/]
    - expected loss: [ or ]

## permission upper as map
[authorization user] → [authentication ] → [day user] → [administrator] → [system ]

Read the full file on GitHub · 77 lines

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. 5d ago First seen · 77 lines · 32 tokens per session scan A 0adfd5e8fdc1

Subscribe to this mod's changes

pentest-reporter is an agent published in the GitHub repository revfactory/harness-100 (1,260 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 664 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 2026-09-03.