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/moshcoder/moshcode/discovergit clone --depth 1 https://github.com/moshcoder/moshcodeWhat 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 | $0.00016 | $0.00377 |
| Opus 5 | $0.00008 | $0.00188 |
| Sonnet 5 | $0.00003 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
discover 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(moshcode stocks:*), Bash(curl -sS https://advis0r.com/api/:*) What it actually says
Task
Rank candidates for $ARGUMENTS (no topic → the default watchlist).
moshcode stocks discover $ARGUMENTS --limit 10 --json
Fallback: curl -sS --max-time 180 "https://advis0r.com/api/discover?topic=<url-encoded>&provider=offline&horizon=2&limit=10"
This route runs an analysis per candidate and can take minutes. Tell the user it is working before you start, and do not retry on a timeout — re-running it costs the same minutes again.
Reading the response
candidates is ranked, each with rank, ticker, companyName, lastPrice,
overallScore, confidence, classification, thesis, primaryCatalyst,
mainRisk, independentConfirmation, plus liquidity fields
(bidAskSpreadPercent, avgVolume, float, marketCap).
Rules
- Lead with
rank,ticker,overallScore, andclassification. - Print
mainRisknext to every thesis. A ranked list that shows only the bull case is a pitch, not research. provider: offlinemeans these scores are deterministic rules, not a model. Say which provider produced the ranking.- Flag illiquidity: a wide
bidAskSpreadPercentor thinavgVolumematters more than the score for anything small-cap. - End with the response's own
disclaimer.
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 · 38 lines · 16 tokens per session scan A ac569811439d
discover is a command published in the GitHub repository moshcoder/moshcode (2 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 377 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
opsx-propose
Propose a new change - create it and generate all artifacts in one step.
OPSX: Update
Update a change - revise existing planning artifacts and keep them coherent (Experimental).
opsx-apply
Implement tasks from an OpenSpec change (Experimental).
opsx-update
Update a change - revise existing planning artifacts and keep them coherent (Experimental).
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
OPSX: Propose
Propose a new change - create it and generate all artifacts in one step.