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/hashgraph-online/hol-guard/recallgit clone --depth 1 https://github.com/hashgraph-online/hol-guardWrote 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.
[](https://agentmods.dev/commands/hashgraph-online/hol-guard/recall)<a href="https://agentmods.dev/commands/hashgraph-online/hol-guard/recall"><img src="https://agentmods.dev/badge/commands/hashgraph-online/hol-guard/recall.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00004 | $0.00017 |
| Opus 5 | $0.00002 | $0.00009 |
| Sonnet 5 | $0.00001 | $0.00003 |
| Haiku 4.5 | $0.00000 | $0.00002 |
Grade A, and why
recall 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 5d 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.
What it actually says
Recall context for $ARGUMENTS.
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.
- 5d ago First seen · 6 lines · 4 tokens per session scan A 1a6d6fb417db
recall is a command published in the GitHub repository hashgraph-online/hol-guard (534 stars, last pushed today), licensed Apache-2.0. It adds 4 tokens to every session and 17 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
release
Run ../../hooks/session-start.ps1 and ../../scripts/release.py.
red-team
Red-team a RUNNING AI agent you own/are authorized to test; a finding is CONFIRMED only when the exploit's proof marker returns. Authorized, disposable-env testing only.
static-scan
Statically triage an AI agent's SOURCE for candidate vulnerable paths (RT-1..RT-9). Candidate != vuln — confirm with /red-team.
fix
Apply intelligent, contextual security fixes to AI agent vulnerabilities. Fix prompt injection, output handling, tool security, data leaks, memory issues, supply chain, and behavioral risks. Use when user says fix, asks to remediate a recommendation (REC-XXX), apply security patches, or resolve vulnerabilities.
scan
Run comprehensive static security analysis on AI agent code using OWASP LLM Top 10 framework. Analyze prompts, outputs, tools, data handling, memory, supply chain, and behavioral patterns. Use when user asks for security scan, vulnerability check, OWASP analysis, code review for security, or wants to check their AI…
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.