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/tlipoca9/devgen/publishgit clone --depth 1 https://github.com/tlipoca9/devgenWhat 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 | $0.02059 |
| Opus 5 | $0.00008 | $0.01030 |
| Sonnet 5 | $0.00003 | $0.00412 |
| Haiku 4.5 | $0.00002 | $0.00206 |
Grade A, and why
publish 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.
How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publish Workflow
You are helping a developer release a new version of devgen. Follow a systematic approach: gather context, check interfaces, build, publish, and create releases.
Core Principles
- Step-by-step execution: Complete each phase before moving to the next
- Conditional logic: Skip unnecessary steps based on actual changes
- Use TodoWrite: Track all progress throughout
- Report progress: Briefly report after each major step
Context
- Current version tags: !
git tag --sort=-v:refname | head -5 - Recent commits: !
git log --oneline -5 - Current branch: !
git branch --show-current - Uncommitted changes: !
git status --short
Phase 1: Initialize
Goal: Determine version number and create task checklist
Initial request: $ARGUMENTS
Actions:
- If
$ARGUMENTScontains a version number (e.g.,0.3.0), use it - Otherwise, ask user with AskUserQuestion:
- Suggest patch version (bug fix):
current→next patch - Suggest minor version (new feature):
current→next minor - Allow custom version input
- Suggest patch version (bug fix):
- Create todo list with all phases using TodoWrite
Phase 2: Check Config Interface
Goal: Determine if Config() method needs updating (affects VSCode plugin syntax highlighting)
Actions:
-
Check for generator file changes:
git diff --name-only HEAD~5 | grep -E 'cmd/.*/generator/.*\.go' || echo "NO_CHANGES" -
If NO_CHANGES: Mark complete, proceed to Phase 3
-
If changes exist, check Config() modifications:
git diff HEAD~5 -- cmd/enumgen/generator/generator.go cmd/validategen/generator/generator.go | grep -A 20 'func.*Config()' -
Decision logic:
- If
Annotationsarray changed → Update needed:- Modify
cmd/<tool>/generator/generator.go - Update
cmd/<tool>/rules/*.md - Run
devgen rules --agent kiro -w
- Modify
- If only internal logic changed → No update needed
- If
Phase 3: Check Rules Interface
Goal: Determine if Rules documentation needs updating (affects AI usage)
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 · 303 lines · 16 tokens per session scan A ef56fad945d4
publish is a command published in the GitHub repository tlipoca9/devgen (5 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 2,059 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
introduce-me
Generate a 2-paragraph personal introduction using the mcp-me introduceme MCP prompt.
ask-about-me
Ask a question about the user's personal profile via the mcp-me MCP server.
documentation
Perform comprehensive documentation and code quality review of the u-he-preset-randomizer project.
publish
Publish a new version of the notebookmd package. Follow these steps exactly.
context
Load project context from AGENTS.md.
Generate PRPROMPTS
Generate all 32 PRPROMPTS files from PRD with strict PRP pattern.