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/abilityai/trinity/request-researchgit clone --depth 1 https://github.com/Abilityai/trinityWhat 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 | $0.00008 | $0.00452 |
| Opus 5 | $0.00004 | $0.00226 |
| Sonnet 5 | $0.00002 | $0.00090 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
request-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.
What it actually says
Request Research
Ask the researcher agent to investigate a specific topic.
Context
The user will provide a topic after this command, like:
/request-research AI agents for content creation/request-research competitor analysis for [company]/request-research emerging trends in [industry]
Steps
-
Parse the Request
- Extract the topic from the user's input
- Formulate a clear research request
-
Find the Researcher Agent
- List available agents:
mcp__trinity__list_agents() - Look for an agent with "researcher" in the name
- Common names:
research-network-researcher(system manifest) orresearcher(individual)
- List available agents:
-
Check Current Findings (Optional)
- List shared-in folder:
ls /home/developer/shared-in/ - Quickly scan existing findings to avoid duplicate research
- Mention if related research already exists
- List shared-in folder:
-
Call the Researcher Use the Trinity MCP tool to request research:
mcp__trinity__chat_with_agent( agent_name="[RESEARCHER_AGENT_NAME]", # Use actual name from step 2 message="/research [TOPIC]" ) -
Report Status
- Confirm the research request was sent
- Explain that findings will appear in the shared folder
- Suggest checking back or running
/briefingafter research completes
Output Format
## Research Request Submitted
**Topic**: [requested topic]
**Sent to**: [researcher agent name]
**Status**: Request delivered
### What Happens Next
1. The researcher agent will investigate the topic
2. Findings will be saved to the shared folder
3. Run `/briefing` to see synthesized results
### Related Existing Research
[If any relevant findings already exist, mention them]
Process the research request now.
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 · 67 lines · 8 tokens per session scan A ad24ebbb0bf8
request-research is a command published in the GitHub repository Abilityai/trinity (496 stars, last pushed 4d ago), licensed Apache-2.0. It adds 8 tokens to every session and 452 once invoked, about $0.0000 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.
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.