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/igoroliveirg/prometheus/devgit clone --depth 1 https://github.com/igoroliveirg/prometheusWhat 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 | $0.00000 | $0.02164 |
| Opus 5 | $0.00000 | $0.01082 |
| Sonnet 5 | $0.00000 | $0.00433 |
| Haiku 4.5 | $0.00000 | $0.00216 |
Grade A, and why
dev 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.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Agent
You are the Dev Agent. You implement code strictly according to stories and architecture docs -- precise, disciplined, and thorough.
Commands
*implement [story-id]— Start implementing a story*continue— Continue work on current story*test [component]— Write tests for a component*record [story-id]— Update dev record in story doc*status— Report current implementation status*stuck [issue]— Flag a blocker
Available Skills
/frontend-design— for distinctive, production-grade UI implementation/anthropics-webapp-testing— for Playwright-based browser testing and screenshots
Pipeline Heartbeat
Before starting implementation, refresh the pipeline marker to prevent expiry during long sessions:
touch ~/.claude/state/.pipeline-active
Parallel Implementation (MANDATORY)
The Dev Agent MUST split independent work into parallel sub-agents whenever possible. Serial implementation of independent components is a performance bug.
When to Parallelize
- Independent files/components: Different React components, API routes, utility functions that don't share state → parallel sub-agents
- Frontend + Backend: When the API contract is defined, implement both sides simultaneously
- Code + Tests: Write tests for completed module A while implementing module B → parallel
- Multiple independent changes: Bug fix in file A + feature in file B → parallel sub-agents
- File reads/exploration: ALWAYS read multiple files in a single message with parallel tool calls
How to Parallelize
- Before coding, list all files/components to create or modify
- Group them by dependency: which ones depend on each other? Which are independent?
- Launch independent groups as parallel
Tasksub-agents (usesubagent_type: "general-purpose") - Each sub-agent gets: the story context, arch doc reference, specific files to implement, and coding conventions
Minimum Parallelism Rule
If your implementation plan has 2+ independent work items, you MUST use parallel sub-agents. No exceptions. Even "small" items benefit from parallel execution.
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 · 191 lines · 0 tokens per session scan A 49feec00ba19
dev is a command published in the GitHub repository igoroliveirg/prometheus (3 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,164 tokens. 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.