Borrowing it
Nothing to install: this file belongs to ManSio/mscodebase-intelligence. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ManSio/mscodebase-intelligence/main/.opencode/command/research.mdgit clone --depth 1 https://github.com/ManSio/mscodebase-intelligenceWrote 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/mansio/mscodebase-intelligence/research)<a href="https://agentmods.dev/commands/mansio/mscodebase-intelligence/research"><img src="https://agentmods.dev/badge/commands/mansio/mscodebase-intelligence/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/mansio/mscodebase-intelligence/research"><img src="https://agentmods.dev/badge/commands/mansio/mscodebase-intelligence/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 | $0.00015 | $0.00418 |
| Opus 5.5 | $0.00006 | $0.00167 |
| Sonnet 5.5 | $0.00003 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
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 26d 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
You are running the RESEARCH phase of the protocol. Your only job is to produce facts the owner can decide on. You are not deciding.
Order of work
- State the question and its falsifier. "Does X work?" is not a question. "Under what condition is X wrong?" is. Write both down before searching.
- Search for the primary source, not the summary. A blog post about a paper is not a source. Prefer the paper, the spec, the release notes, the code.
- Record the negative result. A search that returned nothing useful is data. Write which query failed and what it should have returned. A quietly wrong search result is worse than an empty one — it looks like an answer.
- Freeze the input before you look at the result if this is an experiment
rather than a reading task. See
experiments/*/frozen/. - Separate Verified from Recalled. Anything you did not open in this session is Recalled and must be marked so.
Output
## [🔍 ИССЛЕДОВАНИЕ] <subject>
**Question:** ...
**Falsified if:** ...
**Sources**
| source | what it establishes | verified how |
**Negative results**
- query → what it failed to find
**What this changes in our code**
- concrete file:line, or "nothing"
**Still unknown**
- the question this does NOT answer
Rules
- Two contradictory sources: report both, do not average them.
- A claim with a number gets a referent, or it does not go in the report.
- Do not recommend an action. Present options and their costs; the owner decides.
- If the research contradicts something we published, that is the most important line in the report. Put it first.
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.
- 26d ago First seen · 50 lines · 15 tokens per session scan A e61a578fea04
research is a command published in the GitHub repository ManSio/mscodebase-intelligence (3 stars, last pushed 5d ago), licensed MIT. It adds 15 tokens to every session and 418 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-04.
Other commands, from other repositories
index
Index a folder of documents for semantic search.
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.
react-native
Command "react-native" from getsentry/toolkit, covering xcode build step (react-native xcode) and important notes.
ingest-dev
Ingest a URL, directory, or file into your knowledge base. remember = a specific durable fact, ingest = a URL, learn = a distilled lesson that gets retrieval preference.
sugar-task
Create a comprehensive Sugar task with rich context and metadata.
resume
Auto-detect and resume any interrupted Plan Cascade task. Detects mega-plan, hybrid-worktree, or hybrid-auto context and routes to the appropriate resume command.