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/approve-mergegit clone --depth 1 https://github.com/xsovad06/sovaWrote 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/xsovad06/sova/approve-merge)<a href="https://agentmods.dev/commands/xsovad06/sova/approve-merge"><img src="https://agentmods.dev/badge/commands/xsovad06/sova/approve-merge.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 | $0.00020 | $0.02220 |
| Opus 5 | $0.00010 | $0.01110 |
| Sonnet 5 | $0.00004 | $0.00444 |
| Haiku 4.5 | $0.00002 | $0.00222 |
Grade B, and why
approve-merge scanned grade B with 1 finding 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/agent-control/handoff.json 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Approve Merge
Merge a PR and perform post-merge cleanup. This command is the final step in the shipping pipeline -- it runs after the PR has been rebased, CI has passed, and the user has approved the merge from the dashboard.
# Benchmark logging (entry)
bash .claude/benchmark/log.sh "approve_merge_start" "" "" 2>/dev/null || true
PR: $ARGUMENTS
Instructions
You are an autonomous agent handling the merge and cleanup of an approved PR.
1. Read Handoff Context
Check if a handoff file exists from a previous agent:
cat .claude/agent-control/handoff.json 2>/dev/null
If present, extract pr_number, issue, and branch from it. If not present, parse the arguments directly.
2. Pre-Merge Verification
# Verify PR is still approved and mergeable
gh pr view <PR_NUMBER> --json state,reviewDecision,mergeable,statusCheckRollup,headRefName,baseRefName
# Check CI status
gh pr checks <PR_NUMBER>
Verify:
- PR state is
OPEN - PR is mergeable (no conflicts)
Note: formal GitHub review approval is NOT required. The user triggering this command from the dashboard is the approval. Log the review status for the record, but proceed regardless.
If CI checks are still pending, poll in a loop. Replace <PR_NUMBER> with the actual PR number from context before executing the loop as a single Bash tool call. Requires gh CLI v2.32+ (for the bucket field).
# Set the PR number once at the top -- substitute from context
PR_NUM=<PR_NUMBER>
# Poll CI checks in a loop (30 iterations x 30s = 15 minutes max)
# Uses `bucket` (not `state`) -- bucket normalizes raw states into: pass, fail, pending, skipping, cancel
# Grace period: first 5 iterations (2.5 min) tolerate TOTAL=0 for checks to register after push
for i in $(seq 1 30); do
echo "--- CI poll attempt $i/30 ---"
CHECKS_JSON=$(gh pr checks "$PR_NUM" --json name,bucket 2>/dev/null || echo "[]")
echo "$CHECKS_JSON" | jq -r '.[] | "\(.bucket)\t\(.name)"'
STATS=$(echo "$CHECKS_JSON" | jq -r '
(length | tostring) + "\t" +
([.[] | select(.bucket == "pending")] | length | tostring) + "\t" +
([.[] | select(.bucket == "fail" or .bucket == "cancel")] | length | tostring)
' 2>/dev/null) || { echo "Failed to parse CI check status"; break; }
IFS=$'\t' read -r TOTAL PENDING FAILED <<< "$STATS"
if [ "$TOTAL" -eq 0 ]; then
if [ "$i" -lt 5 ]; then
echo "No checks registered yet (grace period $i/5)"
sleep 30
continue
else
echo "NO_CHECKS: no CI checks configured (grace period expired)"
break
fi
fi
if [ "$PENDING" -eq 0 ]; then
if [ "$FAILED" -gt 0 ]; then
echo "CI FAILED: $FAILED check(s) failed"
break
else
echo "CI PASSED: all $TOTAL checks passed"
break
fi
fi
if [ "$i" -eq 30 ]; then
echo "CI TIMEOUT: checks still pending after 15 minutes"
break
fi
sleep 30
done
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.
- 4d ago First seen · 218 lines · 20 tokens per session scan B a18ee04fb2d3
approve-merge is a command published in the GitHub repository xsovad06/sova (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 20 tokens to every session and 2,220 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
dashboard
Phase 3 monitoring — System health, execution insights, and velocity analytics.
doctor
Check the health of a KARIMO installation, identify issues, and provide actionable recommendations.
run
Execute an approved PRD using feature branch workflow (v7.0). This command generates briefs, auto-reviews them, allows user iteration, and then orchestrates execution.
merge
Consolidate feature branch changes and create final PR to main. This completes the v5.0 feature branch workflow after all task PRs have been merged.
greptile-review
Execute the full Greptile review cycle on a PR, looping until score meets threshold or circuit breaker triggers.
update
Check for and apply KARIMO updates from GitHub releases.