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/oborchers/fractional-ctoWrote 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/oborchers/fractional-cto/research)<a href="https://agentmods.dev/commands/oborchers/fractional-cto/research"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/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/oborchers/fractional-cto/research"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/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 | $0.00025 | $0.01852 |
| Opus 5 | $0.00013 | $0.00926 |
| Sonnet 5 | $0.00005 | $0.00370 |
| Haiku 4.5 | $0.00003 | $0.00185 |
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 9d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conduct structured deep research on the given topic using the deep-research skills (research-methodology, source-evaluation, hallucination-prevention, synthesis-and-reporting).
Follow this process:
Step 1: Topic Capture
If no research topic was provided as an argument, ask the user to describe what they want to research.
Step 2: Query Analysis and Scope Refinement
Analyze the research query for complexity and scope. If the query is vague or overly broad, use AskUserQuestion to ask 2-3 clarifying questions that narrow the scope — modeling how Claude's desktop deep research feature refines queries before committing resources.
Example clarifying questions:
- "What specific aspect of [topic] matters most for your use case?"
- "Are you looking for [aspect A] or [aspect B], or both?"
- "Should this focus on [domain/timeframe/technology]?"
Once scope is clear, restate the refined research question and present it to the user.
Step 3: Confirm or Refine
Use AskUserQuestion to ask the user how to proceed:
- Start research — proceed with the stated research question
- Refine the question — iterate on the scope before committing
If the user chooses to refine, they provide adjustments. Return to Step 2. This loop can repeat until the user is satisfied.
Step 4: Decomposition and Research Plan
Analyze the refined query and determine a decomposition strategy. The number and nature of subtopics emerges from the query — do not prescribe a fixed count. Consult the research-methodology skill for decomposition strategy selection.
Present the research plan to the user:
- The subtopics to investigate
- Which will be researched in parallel
- The output location
Use AskUserQuestion to ask:
- Proceed with this plan — start spawning research workers
- Adjust the plan — modify subtopics before starting
Step 5: Output Location
Use AskUserQuestion to determine where the output should be written:
- Suggest a default path based on the working directory (e.g.,
./deep-research:research/[topic-slug]/) - Let the user specify a custom path
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.
- 9d ago First seen · 173 lines · 25 tokens per session scan A 5caa1474cae6
research is a command published in the GitHub repository oborchers/fractional-cto (29 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 1,852 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 2026-08-30.
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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.