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/0xsteph/pentest-ai-agents/memorygit clone --depth 1 https://github.com/0xSteph/pentest-ai-agentsWhat 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 | $0.00121 |
| Opus 5 | $0.00000 | $0.00060 |
| Sonnet 5 | $0.00000 | $0.00024 |
| Haiku 4.5 | $0.00000 | $0.00012 |
Grade A, and why
memory 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 yesterday.
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.
What it actually says
{
"name": "memory",
"description": "Update the project memory with what was accomplished in this session",
"prompt": "Update the project memory file at .claude/PROJECT_MEMORY.md with a summary of everything that was done in this session. Include:\n1. What features were added or changed\n2. What bugs were fixed\n3. What decisions were made\n4. What is still TODO\n5. Update version history if applicable\n\nRead the current PROJECT_MEMORY.md first, then update it preserving all existing information while adding the new session's work."
}
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.
- yesterday First seen · 6 lines · 0 tokens per session scan A c3888dbe714b
memory is a command published in the GitHub repository 0xSteph/pentest-ai-agents (2,176 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 121 tokens. 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 2026-08-30.
Other commands, from other repositories
bypass-403
Probe a 403/401 endpoint with the most-paid bypass tricks (header injection, path encoding, method swap, WAF fingerprint, vendor-specific). Wraps byp4xx when installed; otherwise runs a built-in matrix of 38+ techniques. Usage: /bypass-403 | /bypass-403 -l.
triage
Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage.
cors
Scan an endpoint for CORS misconfiguration — arbitrary-origin reflection, null-origin trust, credential exposure, suffix/prefix regex bypass, scheme downgrade. Usage: /cors [--cookie "session=..."] | /cors -l urls.txt.
memory-gc
Inspect or rotate hunt-memory JSONL files (audit.jsonl, patterns.jsonl, journal.jsonl). Caps file size and keeps N rotated backups so memory does not grow unbounded.
nosqli
NoSQL injection scanner (MongoDB/Mongoose/operator-injection DBs) — auth bypass via $ne/$gt operators, bracket-syntax query injection, $where time-based blind. Usage: /nosqli --login --user-field email --pass-field password.
remember
Log current finding or successful pattern to hunt memory. Auto-fills from /validate output if available. Usage: /remember.