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/xsovad06/sova/researchgit clone --depth 1 https://github.com/xsovad06/sovaWhat 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 | $0.00016 | $0.01390 |
| Opus 5 | $0.00008 | $0.00695 |
| Sonnet 5 | $0.00003 | $0.00278 |
| Haiku 4.5 | $0.00002 | $0.00139 |
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.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research
Investigate a task's codebase impact and produce a structured research assessment. Designed for autonomous execution -- always writes findings back to the tracker. For interactive pre-development planning, use /spec instead.
Task: $ARGUMENTS
Instructions
Step 1: Fetch the Task
Get the issue number or ticket key from $ARGUMENTS. If empty, stop with an error.
Determine the task source by reading sova.toml (if it exists) and checking [task_source] type.
GitHub (default, or no sova.toml):
gh issue view $ARGUMENTS --json number,title,body,labels,milestone
JIRA (task_source.type = "jira"):
jira issue view $ARGUMENTS --plain
Save the original description verbatim.
If the issue has no description or body, report "Issue has no description; needs specification before research" and stop.
If the issue body already contains a ## Research section, report "Issue already has a research section; ready for development" and stop.
Step 2: Read Project Context
Read whatever exists -- skip files that are missing:
CLAUDE.mdandAGENTS.mdfor project conventions.claude/rules/architecture.mdfor component overview and design decisions.claude/agent-memory/cookbook.mdfor known patterns and past mistakes
Step 3: Explore the Codebase
Based on the issue, investigate the affected areas. Use file reads, grep, and search -- do not guess from file names alone.
- Identify affected files: find every file that needs to be modified, created, or deleted. Read the actual source to confirm.
- Find the pattern: locate the closest existing implementation to follow. Note specific file paths, class names, and method signatures.
- Check for data model changes: determine if DB models, schemas, or migrations are needed.
- Check for API changes: identify new or modified endpoints with request/response shapes.
- Find reusable code: identify utilities, base classes, test fixtures, and patterns that the implementation should use. Reference specific functions and classes.
- Anticipate edge cases: based on reading the actual code, identify failure modes and edge cases not obvious from the issue description.
- Check for UI implications: templates, components, user-facing behavior changes.
- Design implementation approach: produce a concrete 3-6 step plan referencing specific files.
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 · 169 lines · 16 tokens per session scan A 18b0c79685ea
research is a command published in the GitHub repository xsovad06/sova (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,390 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
align
Unified alignment command (--project, --docs, --retrofit, --content).
implement-fix
Minimal pipeline for test-fixing tasks.
create-issue
Create GitHub issue with automated research (--quick for fast mode).
plan
Create a validated planning document with adversarial critique before implementation.
worktree
Manage git worktrees (--list default, --status, --review, --merge, --discard).
refactor
Unified code, docs, and test optimization -- shape analysis, waste detection, dead code, doc redundancy.