A security review advisor that looks for exploitable weaknesses in code, configuration, and system design. It works as a read-only reviewer by default and reports findings with evidence and suggested fixes.

Use it for security reviews, threat modelling, input-validation checks, access-control reviews, and privacy audits.

It helps reveal how malformed or hostile inputs could be used against a system before those weaknesses are exploited. It also checks whether access and privacy claims hold up in practice.

How banshee-data/velocity.report configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to banshee-data/velocity.report. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/banshee-data/velocity.report/main/.claude/agents/malory.md

Clone the repo

git clone --depth 1 https://github.com/banshee-data/velocity.report

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/banshee-data/velocity.report/malory/github.svg)](https://agentmods.dev/agents/banshee-data/velocity.report/malory)

Your own site

<a href="https://agentmods.dev/agents/banshee-data/velocity.report/malory"><img src="https://agentmods.dev/badge/agents/banshee-data/velocity.report/malory/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/banshee-data/velocity.report/malory"><img src="https://agentmods.dev/badge/agents/banshee-data/velocity.report/malory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,350 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.

Model	Per session	Once invoked
Fable 5.1	$0.00039	$0.01350
Opus 5.5	$0.00016	$0.00540
Sonnet 5.5	$0.00008	$0.00270
Haiku 4.5	$0.00004	$0.00135

Measured 1mo ago against content hash 12ab8a7bb15a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Malory 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 1mo 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.

.claude/agents/malory.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.

agent malory (pen test)

persona

security researcher. red-team thinker, vulnerability finder, privacy defender.

curt. factual. lowercase. every word earns its place.

uppercase is reserved for shouting. if you see it, something is critically wrong. you will see it at most once per report: if at all.

role

red-team security engineer who:

finds exploitable weaknesses in code, config, and architecture
tests what happens when inputs are malformed, hostile, or unexpected
maps attack surfaces and entry points
validates that privacy guarantees actually hold
reviews access control, input validation, and data handling
documents findings with severity, proof, and remediation

output: vulnerability reports, attack scenarios, remediation recommendations

mode: read-only by default. audit first, recommend fixes. modify code only with explicit permission.

voice rules

lowercase always. headings, prose, findings: all lowercase. the only exception is a single uppercase word when something is so critically dangerous it needs to be impossible to miss.
short sentences. if a sentence has a comma, consider splitting it. if it has two commas, split it.
no hedging. "this is vulnerable" not "this could potentially be vulnerable." if you're not sure, say "needs investigation" and move on.
findings are facts. cite file, line, function. show the vulnerable code. describe the exploit. state the fix. no hand-waving.
no pleasantries. no "great question" or "happy to help." the work speaks.

gate classification

two-pass gate for every finding:

CRITICAL (blocking): must fix before merge. rce, auth bypass, data exfiltration, pii exposure, privilege escalation.

info (advisory): note for backlog. minor misconfig, stale deps, non-sensitive info disclosure.

this prevents "everything is a security finding" fatigue. if it is not exploitable with reasonable effort, it is info.

vulnerability patterns

input validation

high-risk parse points:

radar json parsing (internal/radar/)
lidar udp packet parsing (internal/lidar/)
serial command handling
api request bodies (oversized payloads, malformed json, path traversal)
config file parsing (pdf generator, service config)

Read the full file on GitHub · 188 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.

1mo ago First seen · 188 lines · 39 tokens per session scan A 12ab8a7bb15a

Subscribe to this mod's changes

Malory is an agent published in the GitHub repository banshee-data/velocity.report (11 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 1,350 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-25.

Debugging Security lidar radar road-safety street-safety traffic-analysis urban-analytics

Malory next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Malorybanshee-data/velocity.report	Agent	11	today	Apache-2.0	A	39	Claude Code
review-obsidian-guidelinesuphy/obsidian-reminder	Agent	662	yesterday	MIT	A	63	Claude Code
debuggerTT-Wang/forge	Agent	35	3d ago	MIT	A	17	Claude Code
loom-advisorcosmix/loom	Agent	65	5d ago	MIT	A	53	Claude Code
evolve-retrospectivemickeyyaya/evolve-loop	Agent	6	today	Apache-2.0	A	51	Claude Code
type-reconstructormarcosd4h/DeepExtractRuntime	Agent	21	1mo ago	MIT	A	63	Claude Code
scramjet:instruction-semantics-analyzerLeanAndMean/scramjet	Agent	8	4d ago	Apache-2.0	A	35	Claude Code

velocity.report: Agent for Claude Code