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/review-fullgit 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 | $0.00026 | $0.00886 |
| Opus 5 | $0.00013 | $0.00443 |
| Sonnet 5 | $0.00005 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
review-full 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full Review Pipeline
Run a complete pre-push quality pipeline: simplify code, review for issues, then organize commits into clean history.
# Benchmark logging (entry)
bash .claude/benchmark/log.sh "review_start" "" "" 2>/dev/null || true
Scope: $ARGUMENTS
Phase 1: Simplify
Follow the /simplify workflow -- review all changed code for opportunities to reduce complexity:
-
Get the diff scope:
git diff main..HEAD --stat git diff --cached --stat git diff --stat -
For each changed file, read the entire file and check:
- Code reuse: does new code duplicate existing utilities or helpers? Search the codebase.
- Over-engineering: unnecessary abstractions, premature generalization, excessive configurability
- Dead code: unused imports, unreachable branches, commented-out code
- Redundancy: repeated logic that could be a shared helper (only if 3+ occurrences)
- Complexity: can any function be simplified without losing clarity?
- Efficiency: redundant computations, repeated file reads, duplicate API calls
-
Apply simplifications directly. After each change, verify tests still pass (see CLAUDE.md for commands).
-
If no simplifications are needed, state that and move on.
Phase 2: Review
Follow the /review command workflow:
- Review all changed files for bugs, security, performance, test coverage, consistency, doc freshness, and scout rule (fix pre-existing issues in touched files).
- Score each finding (1-10 priority). Address all findings (fix or acknowledge with justification).
- Run the full CI-equivalent checks:
{{ check_cmd }}. Fix any failures before proceeding. - Report findings in the standard review format.
See /review for the full review checklist and scoring criteria.
Phase 3: Organize Commits
Follow the /rearrange-commits command workflow:
- Soft reset all commits back to origin/main (stash uncommitted changes first if needed).
- Create small, logical, atomic commits in dependency order.
- Verify: all changes committed, each commit atomic, total diff matches original.
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 · 106 lines · 26 tokens per session scan A ab647de8de51
review-full is a command published in the GitHub repository xsovad06/sova (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 26 tokens to every session and 886 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).
commit
Based on the above changes, create a single git commit.
commit-push-pr
Commit, push, and open a PR.
speckit.git.commit
Auto-commit changes after a Spec Kit command completes.
commit-all
Group all changes semantically and commit each group separately.
commit
Based on the above changes, create a single git commit.