payload-crafter

payload-crafter is an agent for Claude Code from TyrusRC/praetor. It costs 32 tokens per session (768 once invoked), scanned A, original, Apache-2.0.

A security-testing agent that creates alternative test inputs when a web filter or WAF blocks standard inputs. A WAF is a web application firewall that filters potentially dangerous requests.

In plain words
What is it for?
Use it for authorized testing of a specific endpoint and parameter, including mapping filter behavior, trying encoded variants, probing known vulnerabilities, and confirming the result.
Why use it?
It helps determine whether a blocked input is truly prevented or whether the filter can be bypassed, while reporting when the filter remains too strong.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

Good fit Use it for authorized testing of a specific endpoint and parameter, including mapping filter behavior, trying encoded variants, probing known vulnerabilities, and confirming the result.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/tyrusrc/praetor/payload-crafter
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/TyrusRC/praetor

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 payload-crafter

README.md
[![agentmods](https://agentmods.dev/badge/agents/tyrusrc/praetor/payload-crafter.svg)](https://agentmods.dev/agents/tyrusrc/praetor/payload-crafter)
Your own site
<a href="https://agentmods.dev/agents/tyrusrc/praetor/payload-crafter"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/payload-crafter.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 768 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 $0.00768
Opus 5 $0.00016 $0.00384
Sonnet 5 $0.00006 $0.00154
Haiku 4.5 $0.00003 $0.00077

Measured 8d ago against content hash 6b3a6c153288, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

payload-crafter 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 8d 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/payload-crafter.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

payload-crafter

You craft bypasses for filters. Standard payloads from get_payloads failed; your job is to map the filter and find the gap.

FIRST-MOVE PLAYBOOK

1. if vuln_class matches a known CVE-id:
       probe_cve_with_variants(cve_id=..., target_url=..., max_variants=12)
       — variant generators cover encoding chains, multipart, $-ref, canary echoes
2. else:
       fuzz_parameter(index, parameter, payloads=[single chars]) — map filter
       get_payloads(category, context, waf_bypass=True)
       mutate_payload(base, mutations=['case','double_url','unicode_normalize','base64_split','collide_homoglyph'])
       transform_chain([encoders...]) — multi-layer
3. confirm_<class>(target, parameter, payload=mutated) — VerdictResult
4. return: working bypass payload OR "filter too strong — alternative: <route via other endpoint/header>"

Inputs

  • domain (required)
  • endpoint (required)
  • parameter (required)
  • vuln_class (required)
  • blocked_payloads (optional) — what the operator already tried
  • session_name (optional)

Tools You Use

fuzz_parameter, get_payloads, decode_encode, session_request, probe_endpoint, save_target_notes, transform_chain, mutate_payload, smart_decode

Workflow

  1. check_scope — abort if out of scope
  2. Filter mapping: send {benign, single-char, multi-char} triplets to identify what's blocked at what stage (WAF / app-layer / output encoder)
  3. Pick bypass class by filter type:
    • Char filter → encoding (URL × N, double-URL, base64, unicode, HTML entities)
    • Keyword filter → comments, case variation, alternative syntax
    • Length filter → minified payload
    • Context filter → break out of context first (quote escape, comment, attribute)
  4. mutate_payload for variants; transform_chain for encoding stacks
  5. Verify bypass with probe_endpoint — must produce class-appropriate evidence
  6. Save the working bypass to .burp-intel/<domain>/notes.md via save_target_notes

Returns

Read the full file on GitHub · 74 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. 8d ago First seen · 74 lines · 32 tokens per session scan A 6b3a6c153288

Subscribe to this mod's changes

payload-crafter is an agent published in the GitHub repository TyrusRC/praetor (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 768 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 2026-08-31.

Related

Other agents, from other repositories

senior-pentester

20+ year offensive security reviewer. Receives one logical firewall's normalized ruleset (already through deterministic detectors) and flags semantic concerns detectors can't catch — business-logic gaps, trust-boundary violations, unusual service combos. 2-4 instances dispatched in parallel during /launch.

transilienceai/communitytools · 62 tokens

ciso-reviewer

Business-impact gate. Adjusts severity based on asset criticality, engagement regulatory overlay, and compensating controls. Does NOT veto findings.

transilienceai/communitytools · 32 tokens

citation-verifier

Deterministic (not LLM). Greps every finding's quoted rule text in its cited source file and verifies framework citation versions match the pinned set. Mismatches → quarantine.

transilienceai/communitytools · 41 tokens

cto-reviewer

Technical truth gate. Re-derives each finding's claim from the parsed rule AST and returns yes/no/uncertain. Uncertain findings route to held/ for human reviewer.

transilienceai/communitytools · 40 tokens

qa-reviewer

Editorial gate. Final pass on phrasing, framework-citation-version accuracy, cross-finding consistency. Flags (never blocks) findings that need author attention.

transilienceai/communitytools · 35 tokens

agent-dynamic-tester

Role brief for the dynamic-tester agent — performs runtime / negative testing (Perform / Test methods) against an authorized running instance for PCI SSS v2.0 dynamic Test Requirements, capturing dynamicobservation evidence. When no running instance is authorized, the requirement is REQUIRESMANUALREVIEW, never a faked…

transilienceai/communitytools · 73 tokens