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/mtthsnc/tempest/bcpgit clone --depth 1 https://github.com/mtthsnc/tempestWhat 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 | $0.00024 | $0.00153 |
| Opus 5 | $0.00012 | $0.00077 |
| Sonnet 5 | $0.00005 | $0.00031 |
| Haiku 4.5 | $0.00002 | $0.00015 |
Grade A, and why
bcp 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 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.
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
Load and follow the bcp skill to bring a Brand Context Protocol into the work.
Request: $ARGUMENTS
Find or scaffold the brand repo (github.com/mtthsnc/bcp), then route to BCP's own skills —
brand-truth to capture/extend the source, landing-page (or similar) to produce a traced
deliverable, and brand-check to score it before shipping. Don't invent brand facts here; the BCP
repo is the source of truth.
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 · 13 lines · 24 tokens per session scan A 85a70a1b8197
bcp is a command published in the GitHub repository mtthsnc/tempest (2 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 153 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.
Other commands, from other repositories
factory-tune
Review factory performance and propose deliberate constraint changes - tighten where a gate let something through, loosen where a class of change has been green long enough.
init
Create local runtime config and the first admin user.
index
Command "index" from nordbyte/nordrelay, covering cli command reference, commands and global options.
remote
Start, stop, restart, inspect, or troubleshoot the local NordRelay process.
service
Install, remove, or inspect OS service integration.
foreground
Run the connector in the current terminal.