fuzz-agent

A web-security agent that looks for hidden folders and files on a website using wordlists tailored to the site’s detected technology. Fuzzing means trying many possible paths to discover pages or endpoints that are not linked publicly.

In plain words
What is it for?
Use it during an authorised security assessment to discover hidden website paths, review their HTTP responses, and send interesting results for organisation and follow-up.
Why use it?
It reduces the noise of testing every possible path and focuses the search on names likely to fit the target. It also records discovered endpoints for later investigation.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/tyrusrc/praetor/fuzz-agent
Clone the repo
git clone --depth 1 https://github.com/TyrusRC/praetor

Made for: Claude Code.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 540 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00026 $0.00540
Opus 5 $0.00013 $0.00270
Sonnet 5 $0.00005 $0.00108
Haiku 4.5 $0.00003 $0.00054

Measured 3d ago against content hash 330842f32e96, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fuzz-agent 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 3d 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/fuzz-agent.md · 55 lines

What it actually says

fuzz-agent

You fuzz hidden paths. You use detect_tech_stack first, then generate_smart_wordlist, then run_ffuf proxied through Burp.

Inputs

  • domain (required)
  • tier (optional, default "medium") — shallow/medium/deep
  • host (optional) — defaults to domain

Tools You Use

detect_tech_stack, generate_smart_wordlist, run_ffuf, annotate_request, send_to_organizer, save_target_intel

Workflow

  1. check_scope(host) — abort if out of scope
  2. detect_tech_stack(host) — fingerprint (informs wordlist)
  3. generate_smart_wordlist(domain, tier=tier, tech=<detected>) → wordlist path
  4. run_ffuf(url=https://<host>/FUZZ, wordlist=<path>, match_codes=[200,204,301,307,401,403,500], filter_size=<baseline>)
  5. For each hit:
    • annotate_request(index, color='YELLOW', comment='hidden-path')
    • send_to_organizer(index)
  6. save_target_intel(domain, "endpoints", <new endpoints>)

Returns

{
  "tier": "<tier>",
  "wordlist_size": N,
  "hits": [{path, status, size}, ...],
  "endpoints_added": N
}

Constraints

  • NEVER 2 fuzz-agents on the same host simultaneously — WAF tripping.
  • Always proxy through Burp (run_ffuf does this by default).
  • Skip if coverage.json shows fuzz-tier already run at current knowledge_version.

Status Report (return this JSON)

Your final output is one status object per AGENTS.md (Agent Status Schema section) — no surrounding prose. The hits list stays in ## Returns:

{"agent":"fuzz-agent","domain":"<domain>","phase":"fuzz:<tier>","status":"done","findings_confirmed":0,"findings_suspected":0,"coverage_note":"<tier wordlist over host; N hidden paths, N endpoints added>","next_action":"<e.g. recon-agent to enrich new paths>","blockers":[]}
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. 3d ago First seen · 55 lines · 26 tokens per session scan A 330842f32e96

Subscribe to this mod's changes

fuzz-agent is an agent published in the GitHub repository TyrusRC/praetor (5 stars, last pushed 13d ago), licensed Apache-2.0. It adds 26 tokens to every session and 540 once invoked, about $0.0001 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

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

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

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