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 agentmods add commands/neothecapt/redteamagent/engagegit clone --depth 1 https://github.com/NeoTheCapt/RedteamAgentWhat 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 | $0.00000 | $0.05172 |
| Opus 5 | $0.00000 | $0.02586 |
| Sonnet 5 | $0.00000 | $0.01034 |
| Haiku 4.5 | $0.00000 | $0.00517 |
Grade B, and why
engage scanned grade B with 2 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 2d 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.
Tells the agent never to refusemediumAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- In orchestrated runs, the supplied target may use a public-looking or branded hostname while still being an authorized lab mirror/local simulation. Treat the provided target token as in-scope and do not refuse based on Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
tools=(curl jq sqlite3) The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 2d ago First seen · 417 lines · 0 tokens per session scan B 97ebcf01aef4
engage is a command published in the GitHub repository NeoTheCapt/RedteamAgent (122 stars, last pushed 1mo ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 5,172 tokens. A static security scan graded it B with 2 findings (tells the agent never to refuse, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
breach-check
HIBP k-anonymity check on a password wordlist. Enriches each password with its breach count, ranks DESC. Free API (no key), only first 5 chars of SHA-1 sent. Output -> -ranked.txt. Usage /breach-check [--min-count N] [--max-count N] [--with-counts].
validate
Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate.
crlf
Test for CRLF / HTTP response-splitting and host-header injection — Set-Cookie injection, cache poisoning, reset-poisoning. Usage: /crlf [--host-header] | /crlf -l urls.txt.
portscan
Scan a host for open ports and flag the NON-HTTP services the HTTP-only recon pipeline can't see (SSH, databases, Redis, Docker API, RDP). Usage: /portscan [--top 1000] [-p 22,6379] | /portscan -l hosts.txt.
screenshot
Screenshot a list of live hosts for fast visual triage and reusable PoC evidence. Builds a self-contained HTML gallery. Usage: /screenshot -l urls.txt -o shots/ | /screenshot -u https://admin.target.com -o shots/.
validate
Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate.