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/hoursgit 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 | $0.00014 | $0.00391 |
| Opus 5 | $0.00007 | $0.00196 |
| Sonnet 5 | $0.00003 | $0.00078 |
| Haiku 4.5 | $0.00001 | $0.00039 |
Grade A, and why
hours 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 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.
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
Task
billing hours $ARGUMENTS --json
This is the preview of what billing invoice new --from-timer would bill. Same
filters, same grouping, same arithmetic — it writes nothing.
Reading the response
items[]— the line items, each withdescription,quantity(in the rate's own billing unit),unitPriceMajor,amount,hoursandtimerIds.unit— whatquantityis measured in:hours, oragent-hourswhen the rate is priced per agent.hours/units/subtotal— the totals.skipped—{ running, unbillable, alreadyBilled }.
Rules
- Always read
skipped.runningback to the user. Those hours are not missing, they are on a clock that is still ticking and become billable the moment it stops. "Nothing to bill" is misleading when the real answer is "stop the clock first". - Exit 3 means no unbilled hours matched, or the client does not exist. Read the message; it distinguishes them.
- When
unitisagent-hours, explain the multiplier if the user seems surprised: 3 hours with 2 agents is 6 agent-hours.quantity * unitPricealways equalsamount. - If there is no rate, the error says so and names the command that sets one. Do not invent a rate to get past it.
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 · 14 tokens per session scan A 80f40c9eebe4
hours is a command published in the GitHub repository moshcoder/moshcode (2 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 391 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
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.