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/restarter/lets-workflow/researchgit clone --depth 1 https://github.com/restarter/lets-workflowWhat 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 | $0.01589 |
| Opus 5 | $0.00000 | $0.00794 |
| Sonnet 5 | $0.00000 | $0.00318 |
| Haiku 4.5 | $0.00000 | $0.00159 |
Grade A, and why
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 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/lets:research — web-first sourced research
Ask a question about the outside world, get back a concise answer where every non-trivial claim carries a citation — searched and fetched from the live web, cross-checked by a skeptic agent, and honestly labeled where the evidence is thin.
/lets:research which local LLM fits 32GB RAM + RTX 3080?
When to use it (and when not)
/lets:research fills a gap the other consult commands don't cover: its deliverable is a cited synthesis of external facts, not ideas about your project and not an expert's opinion from model knowledge.
| You want | Use | Shape |
|---|---|---|
| An answer to an external/technical question, with sources | /lets:research |
question → sourced answer |
| One expert's take, quick | /lets:ask |
question → expert consult |
| A judgment or ideas about something in your project (a decision or an open question) | /lets:opinion |
decision / open question → project-grounded take (no web) |
| A plan for how to build something | /lets:plan |
task → implementation plan |
Rule of thumb: if the answer should end with a Sources list, it's research. "Which vector DB has the best Go client in 2026?" is research; "how should we add a vector DB to this repo?" is opinion or plan.
Usage
| Form | What happens |
|---|---|
/lets:research <question> |
Research the question, return a cited synthesis. |
/lets:research |
Asks what to research first, then goes. |
/lets:research <question> --workflow |
Same stages, but the research and cross-check run off-context in a Dynamic Workflow — only the final synthesis enters your conversation. |
/lets:research <question> --project |
Also grounds findings against this repo (is X already used here, does it fit our stack), without ever reading outside the project root. |
Without an explicit --workflow, the command offers a run-mode picker: Standard (everything visible in the chat) or Workflow (off-context, only the synthesis returns).
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 · 71 lines · 0 tokens per session scan A f04b6c83c0f6
research is a command published in the GitHub repository restarter/lets-workflow (17 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,589 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 2026-08-30.
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.