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/polarcoding85/convex-agent-skillz/create-featuresgit clone --depth 1 https://github.com/PolarCoding85/convex-agent-skillzWhat 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 | $0.00006 | $0.00442 |
| Opus 5 | $0.00003 | $0.00221 |
| Sonnet 5 | $0.00001 | $0.00088 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
create-features 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
Convert the implementation plan above into a structured feature breakdown. Follow these steps precisely:
1. Directory Setup
- Create
docs/features/if it doesn't exist - Create a sub-folder using kebab-case based on the plan name (e.g.,
docs/features/user-authentication/)
2. Copy Source Plan
- Save the original implementation plan as
_source-plan.mdin the sub-folder
3. Create Overview File
Create 00-overview.md with this structure:
# [Feature Set Name]
## Summary
[Brief description of what this implementation achieves]
## Features
| # | Feature | File | Status | Dependencies |
| --- | ------- | -------------------- | -------------- | ------------ |
| 1 | [Name] | `01-feature-name.md` | ⬜ Not Started | None |
| 2 | [Name] | `02-feature-name.md` | ⬜ Not Started | #1 |
## Status Legend
- ⬜ Not Started
- 🟡 In Progress
- ✅ Complete
- ⛔ Blocked
## Implementation Order
[Recommended sequence based on dependencies]
4. Create Individual Feature Files
For each feature, create a numbered file (e.g., 01-feature-name.md) with:
# Feature: [Name]
## Overview
[What this feature does and why]
## Dependencies
- **Requires:** [List prerequisite features by number, or "None"]
- **Blocks:** [List features that depend on this one]
## Acceptance Criteria
- [ ] [Criterion 1]
- [ ] [Criterion 2]
## Technical Details
[Implementation specifics from the plan]
## Files to Create/Modify
- `path/to/file.ts` - [Purpose]
## Notes
[Any additional context or considerations]
Guidelines
- Extract atomic, independently testable features
- Identify implicit dependencies between features
- Preserve all technical details from the source plan
- Use clear, action-oriented feature names
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 · 86 lines · 6 tokens per session scan A eeee1880be7d
create-features is a command published in the GitHub repository PolarCoding85/convex-agent-skillz (17 stars, last pushed 6mo ago), licensed MIT. It adds 6 tokens to every session and 442 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
burn-rate
Compute the recent 7-day spend trend (burn rate) from daily sessions and per-session cost.
inventory
One-screen inventory of skills, agents, commands, MCP servers, and hooks counts.
cost-today
Quick total cost plus a per-model one-liner from the dashboard pricing engine.
top-spenders
List the top N most expensive Claude Code sessions by inline cost.
status
One-line Agent Monitor health + counts summary from /api/stats.
create-acceptance-criteria
Derive and post confirmed Gherkin acceptance criteria for an issue.