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/find-taskgit 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 | $0.00018 | $0.00627 |
| Opus 5 | $0.00009 | $0.00313 |
| Sonnet 5 | $0.00004 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
find-task 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find Next Task
Browse the GitHub Issues backlog, review sprint priorities, and suggest what to work on next.
Scope: $ARGUMENTS
Instructions
1. Fetch Open Issues
# Assigned issues first
gh issue list --assignee @me --state open --limit 50 --json number,title,labels,milestone,updatedAt,body
# If no assigned issues, broaden to all open
gh issue list --state open --limit 30 --json number,title,labels,milestone,updatedAt
If $ARGUMENTS contains filters (label, milestone), incorporate them:
gh issue list --state open --label "<label>" --milestone "<milestone>" --limit 30
2. Categorize by Status
- Active work: issues with in-progress labels or linked open PRs
- Queued: assigned but not started (backlog, ready)
- Quick wins: small, well-scoped tasks (look for size/effort labels)
- Medium effort: refactors, feature work with clear scope
- Needs refinement: issues with vague descriptions or missing acceptance criteria
- Blocked: issues with blocker labels or dependency on other issues
3. Analyze Each Issue
For each issue, provide:
- Issue number, title, current labels
- Estimated effort: small / medium / large (based on title and description)
- Dependencies: does it block or depend on other issues?
- Suggested priority based on labels, dependencies, and effort
4. Suggest a Plan
- What to finish first (active work)
- What to pick up next (from queued, prioritized by labels and dependencies)
- Quick wins that can be done between larger tasks
- What needs refinement before starting
5. Present and Wait
Present the summary and wait for the user to choose.
6. When the User Selects an Issue
- Assign it (if not already):
gh issue edit <NUMBER> --add-assignee @me - Suggest creating a feature branch:
git checkout -b feat/<short-name> main
7. Re-prioritize (if requested)
- Add/remove labels:
gh issue edit <NUMBER> --add-label "priority:high" - Unassign to defer:
gh issue edit <NUMBER> --remove-assignee @me
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 · 82 lines · 18 tokens per session scan A e5d4b7cc40d6
find-task is a command published in the GitHub repository xsovad06/sova (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 18 tokens to every session and 627 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
implement-fix
Minimal pipeline for test-fixing tasks.
align
Unified alignment command (--project, --docs, --retrofit, --content).
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.