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/deepvista-ai/deepvista-cli/deepvistagit clone --depth 1 https://github.com/DeepVista-AI/deepvista-cliWrote 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/deepvista-ai/deepvista-cli/deepvista)<a href="https://agentmods.dev/commands/deepvista-ai/deepvista-cli/deepvista"><img src="https://agentmods.dev/badge/commands/deepvista-ai/deepvista-cli/deepvista.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.01002 |
| Opus 5 | $0.00012 | $0.00501 |
| Sonnet 5 | $0.00005 | $0.00200 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade A, and why
deepvista 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepVista control surface. Behaviour depends on $ARGUMENTS:
- No argument (or any value other than
run) → print the help block below. run→ execute today's Daily Planning note: launch a subagent per workflow Skill listed in its## Planningsection, then append a consolidated## Summaryback onto the note.
Generation moved server-side. Today's planning note is created by the
DeepVista server agent via the deepvista-daily-planning skill — either on a
schedule you opt into (deepvista schedule activate) or on demand. This command
only processes (runs) a note that already exists. Planning notes are regular
DeepVista notes (type=note) tagged daily-planning + date:YYYYMMDD.
If $ARGUMENTS is empty or not run
Print this verbatim, then stop:
DeepVista — Claude Code commands
/deepvista run— execute today's Daily Planning note. Reads the note's## Planningworkflow chips and runs each workflow Skill with a subagent, then appends the results under a## Summary — <timestamp>block./refresh-skills— resync the DeepVista skill catalog immediately (bypasses the 60-minute throttle).Generating today's plan
- Planning is generated by the DeepVista server, not here. Activate a daily run with
deepvista schedule activate(or--weekly), or ask DeepVista to run thedeepvista-daily-planningskill on demand.deepvista schedule list/deepvista schedule deactivatemanage it.Tips
- Need help with the CLI itself?
deepvista --helpordeepvista <group> --help.
If $ARGUMENTS is run
Execute today's planning note.
Step 1 — Find today's planning note
TODAY=$(date +%Y%m%d)
deepvista --format json card +search "Daily Planning $TODAY" --limit 5
Pick the card whose tags include both daily-planning and date:$TODAY,
then fetch its full body:
deepvista --format json notes get <note-id>
If no note exists for today, stop and tell the user to generate one first —
generation is server-side now: deepvista schedule activate for a recurring
run, or ask DeepVista to run the deepvista-daily-planning skill on demand. Do
not try to generate the plan from this command.
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.
- 5d ago First seen · 116 lines · 24 tokens per session scan A f5efb5130985
deepvista is a command published in the GitHub repository DeepVista-AI/deepvista-cli (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 1,002 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.