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/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 | $0.00007 | $0.00360 |
| Opus 5 | $0.00003 | $0.00180 |
| Sonnet 5 | $0.00001 | $0.00072 |
| 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 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
Research Cycle
Execute a research cycle to discover and document interesting trends.
Steps
-
Ensure Output Directory
- Create
/home/developer/shared-out/findings/if it doesn't exist
- Create
-
Discover Trends Search for trending topics in:
- AI and machine learning developments
- Startup ecosystem news
- Developer tools and productivity
- Technology industry trends
-
Analyze Findings For each interesting discovery:
- Summarize the key points
- Assess potential opportunity or impact
- Rate complexity/effort to pursue
-
Document Results Write findings to
/home/developer/shared-out/findings/:- Create
[YYYY-MM-DD]-findings.mdwith today's date - Update
summary.mdwith cumulative insights (keep last 5 research cycles)
- Create
-
Report Summary Output a brief summary of what was found:
- Number of trends identified
- Top 3 most interesting findings
- Any high-priority items
Output Format
The findings file should follow this structure:
# Research Findings - [DATE]
## Key Trends
- Trend 1: [description]
- Trend 2: [description]
## Opportunities Identified
1. **[Opportunity Name]**
- Description: ...
- Why interesting: ...
- Complexity: Low/Medium/High
## Notable Signals
- [Signal 1]
- [Signal 2]
## Sources
- [Source 1]
- [Source 2]
Execute the research cycle 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 · 66 lines · 7 tokens per session scan A 322b37fcd886
research is a command published in the GitHub repository Abilityai/trinity (496 stars, last pushed 4d ago), licensed Apache-2.0. It adds 7 tokens to every session and 360 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.