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.
git clone --depth 1 https://github.com/loschenbd/claude-agent-boilerplateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/loschenbd/claude-agent-boilerplate/r)<a href="https://agentmods.dev/commands/loschenbd/claude-agent-boilerplate/r"><img src="https://agentmods.dev/badge/commands/loschenbd/claude-agent-boilerplate/r/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/loschenbd/claude-agent-boilerplate/r"><img src="https://agentmods.dev/badge/commands/loschenbd/claude-agent-boilerplate/r.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.00504 |
| Opus 5 | $0.00000 | $0.00252 |
| Sonnet 5 | $0.00000 | $0.00101 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
r 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 5d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run a focused research pass on the codebase before any planning or implementation begins.
Instructions
You are in the Research phase of QRSPI. Your job is to gather objective facts about the codebase — no recommendations, no design opinions, no code changes.
The user will provide either:
- A feature ticket / task description, OR
- A set of targeted questions they've already written
If given a ticket: Extract the key technical unknowns from it, then research those. Do not let the ticket bias your findings — report what is, not what the ticket wants.
If given questions: Answer each question with codebase evidence.
What to produce
Spawn an Explore subagent to investigate. Direct it to find and document:
- Relevant files — exact paths for every file that touches the affected area
- Current patterns — how similar things are already done in this codebase (naming, structure, conventions)
- Data flows — how data moves through the affected area
- Existing types/schemas — relevant TypeScript types, Zod schemas, database table shapes
- Potential collision points — anything that could conflict with or be affected by changes in this area
Output format
Write findings to plans/<task-slug>/research.md using this structure:
# Research: <task name>
## Relevant Files
- `path/to/file.ts` — what it does and why it matters here
## Current Patterns
- <pattern name>: <how it works, with file:line references>
## Data Flow
<trace the relevant flow end-to-end>
## Types & Schemas
- <type/schema name>: `path/to/file.ts:line`
## Collision Points
- <anything that could break or conflict>
## Open Questions
- <anything the research couldn't resolve — flag for Design Discussion>
Rules
- Facts only. No implementation suggestions in this doc.
- Cite everything. Every claim should reference a file path and line number.
- Keep context lean. Use the Explore subagent for grep/glob/read so the main context stays clean.
- Stop here. Do not proceed to planning. Surface the research doc to the user for review.
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.
- 5d ago First seen · 59 lines · 0 tokens per session scan A df3f59f644ef
r is a command published in the GitHub repository loschenbd/claude-agent-boilerplate (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 504 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 2026-09-04.
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.