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/iterate-research)<a href="https://agentmods.dev/commands/loschenbd/claude-agent-boilerplate/iterate-research"><img src="https://agentmods.dev/badge/commands/loschenbd/claude-agent-boilerplate/iterate-research/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/iterate-research"><img src="https://agentmods.dev/badge/commands/loschenbd/claude-agent-boilerplate/iterate-research.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 | $0.00362 |
| Opus 5 | $0.00000 | $0.00181 |
| Sonnet 5 | $0.00000 | $0.00072 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
iterate-research 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.
What it actually says
Re-run the research phase with corrective feedback from the user.
Instructions
You are iterating on a previous research pass. The user has reviewed plans/<task-slug>/research.md and is asking for changes.
Use the user's feedback in this message (the text after /iterate-research) as the corrective direction.
- Read the existing
plans/<task-slug>/research.md - Identify what the feedback wants changed:
- Missing files or patterns to investigate?
- Wrong scope (too broad, too narrow)?
- Specific claims that are wrong?
- A collision point that wasn't surfaced?
- Spawn an
Exploresubagent with explicit corrective direction based on the feedback (not a generic re-research) - Replace
plans/<task-slug>/research.mdwith a new clean version (do not append) - Add a short
## Iteration notessection at the bottom briefly noting what changed in this pass and why - Tell the user: "Research updated. Re-review
plans/<task-slug>/research.md."
Rules
- Replace, don't append. Produce a clean doc, not a diff against the previous version.
- Stop at the same gate. Don't proceed to design — wait for user re-review.
- Treat feedback as ground truth. If the user says a claim is wrong, investigate the codebase and correct it; don't argue.
- Don't invent new patterns. Research is still facts-only — no recommendations.
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 · 28 lines · 0 tokens per session scan A 768629ca99f4
iterate-research 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 362 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.