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/mistakeknot/interdeep/researchgit clone --depth 1 https://github.com/mistakeknot/interdeepWhat 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 | $0.00010 | $0.00357 |
| Opus 5 | $0.00005 | $0.00179 |
| Sonnet 5 | $0.00002 | $0.00071 |
| Haiku 4.5 | $0.00001 | $0.00036 |
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 yesterday.
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
/interdeep:research
Start a deep research session. This command invokes the deep-research skill with optional depth control.
Usage
/interdeep:research <query>
/interdeep:research quick <query>
/interdeep:research balanced <query>
/interdeep:research deep <query>
Examples
/interdeep:research what are the best practices for MCP server design in 2026
/interdeep:research quick trafilatura vs readability comparison
/interdeep:research deep autonomous agent architectures and their failure modes
/interdeep:research balanced recent advances in retrieval-augmented generation
Behavior
- Parse the first argument as a depth mode if it matches
quick,balanced, ordeep. Otherwise treat the entire argument as the query and usebalancedas default. - Invoke the
deep-researchskill with the parsed query and depth mode. - The skill handles the full research pipeline: orient, search, extract, synthesize, persist.
- Returns a structured markdown report in the chat.
Depth Modes
- quick — Fast answer. 1-2 sub-queries, 5 URL limit. Best for factual lookups.
- balanced — Standard research. 3-5 sub-queries, 15 URL limit. Good for most topics.
- deep — Thorough investigation. 5-10 sub-queries, 30+ URLs, thinking gap analysis. Use for complex or high-stakes topics.
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.
- yesterday First seen · 42 lines · 10 tokens per session scan A 562209cfe48d
research is a command published in the GitHub repository mistakeknot/interdeep (0 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 357 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 2026-08-31.
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.