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/catfish-1234/proctor/checkgit clone --depth 1 https://github.com/catfish-1234/proctorWhat 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 | $0.00013 | $0.00325 |
| Opus 5 | $0.00006 | $0.00162 |
| Sonnet 5 | $0.00003 | $0.00065 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
check 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
Run npx @kavishdua/proctor check on the current working changes (add --staged if the user
asked about what is staged rather than what is in the working tree).
Report the findings as they are. For each one, name the rule ID, the file and line, and what the check actually objected to. Do not soften a finding, and do not describe an error-severity finding as a warning.
If there are no findings, say so plainly and stop.
If there are findings, work out for each one whether it is:
- A real problem in the change. Fix the underlying code so the original test passes unaltered. This is the common case and the one to assume unless the evidence says otherwise.
- A genuine, intentional test change. Say why you believe that, and tell the user they can
record it with
npx @kavishdua/proctor approve <RH-ID> <file> --reason "...", which they then need to commit. Do not runapproveyourself: an approval is the user's call, and one added in the same change it excuses has no effect anyway. - A false positive. Explain the specific reason the check misread the diff, rather than asserting it in general terms.
Run npx @kavishdua/proctor check --explain <RH-ID> when you need the full description of a rule.
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 · 26 lines · 13 tokens per session scan A 4c3b07b3ff80
check is a command published in the GitHub repository catfish-1234/proctor (1 stars, last pushed 6d ago), licensed MIT. It adds 13 tokens to every session and 325 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
sum
Distill insights from this conversation into memories.
search
Search Nowledge Mem for relevant memories.
save
Save current session to Nowledge Mem.
status
Check Nowledge Mem connection and server status.
nowledge-read-working-memory
Read today's Working Memory briefing.
import-history
Backfill older CodeBuddy sessions into Nowledge Mem Threads.