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/askgit 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 | $0.00388 |
| Opus 5 | $0.00003 | $0.00194 |
| Sonnet 5 | $0.00001 | $0.00078 |
| Haiku 4.5 | $0.00001 | $0.00039 |
Grade A, and why
ask 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
Answer Strategic Question
Use accumulated research findings to answer the user's question.
Context
The user will provide a question after this command, like:
/ask What opportunities exist in AI agents?/ask What are the main risks we should watch?/ask Should we pursue [specific opportunity]?
Steps
-
Understand the Question
- Parse the user's question
- Identify key topics and themes to search for
-
Search Research Findings
- First, discover the researcher's shared folder:
ls /home/developer/shared-in/ - Look for a folder containing "researcher" in the name
- Read all available findings from that folder's
findings/subdirectory - Look for relevant information matching the question topics
- Note supporting evidence and sources
- First, discover the researcher's shared folder:
-
Synthesize Answer
- Compile relevant findings
- Draw connections between data points
- Form a coherent answer
-
Provide Response
## Question
[Restate the question]
## Answer
[Clear, direct answer based on research]
## Supporting Evidence
1. **[Finding 1]** (from [date])
- [Relevant detail]
2. **[Finding 2]** (from [date])
- [Relevant detail]
## Confidence Level
[High/Medium/Low] - based on [amount of supporting data]
## Caveats
- [Any limitations or gaps in the research]
## Suggested Follow-up
- [Additional research that could help]
- Handle Missing Data
If insufficient research exists:
- State what information is missing
- Suggest running
/request-research [topic]to gather more data
Answer the question 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 · 7 tokens per session scan A 5ccc744eee62
ask 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 388 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.