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/ophis-fi/ophis/debug-ordergit clone --depth 1 https://github.com/ophis-fi/ophisWhat 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 | $0.00010 | $0.00393 |
| Opus 5 | $0.00005 | $0.00197 |
| Sonnet 5 | $0.00002 | $0.00079 |
| Haiku 4.5 | $0.00001 | $0.00039 |
Grade A, and why
debug-order scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
source .env.claude && curl -s -H "X-API-Key: $COW_DEBUG_API_KEY" "https://partners.cow.fi/$NETWORK/restricted/api/v1/debug/order/$ORDER_UID" | jq . The source is not reproduced here
Licensed GPL-3.0
The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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 · 29 lines · 10 tokens per session scan A 95574c94225a
debug-order is a command published in the GitHub repository ophis-fi/ophis (3 stars, last pushed 2d ago), licensed GPL-3.0. It adds 10 tokens to every session and 393 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
deploy
Deploy Suwappu services on Railway. Usage: /deploy [prod|dev] [python-api|python-worker|terminal|api-ts|showcase|all].
status
Check what's actually running: Railway control plane + deep health + logs + CI. Usage: /status [prod|dev] [--quick].
audit
Attacker-minded security audit of scoped files. Traces auth + money-path data flows, streams compact findings incrementally (never one giant end-of-session JSON dump). Usage: /audit [attack-class].
worktree-check
Audit every git worktree for uncommitted, unpushed, or stashed work at risk before any reset/merge/cleanup. Usage: /worktree-check.
audit-fleet
Parallel attacker-minded audit: fan out one security-auditor per attack surface, each streaming findings to disk, then dedupe/rank and file issues. Usage: /audit-fleet [scope hint].
bugclass
Treat one confirmed bug as a class: reproduce, fix, generalize the class, sweep the repo, and fix every instance with one commit each. Usage: /bugclass.