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 agents/ksegit/version-sentinel/version-reviewergit clone --depth 1 https://github.com/KSEGIT/Version-SentinelWhat 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 | $0.00065 | $0.00407 |
| Opus 5 | $0.00032 | $0.00204 |
| Sonnet 5 | $0.00013 | $0.00081 |
| Haiku 4.5 | $0.00006 | $0.00041 |
Grade A, and why
version-reviewer 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.
What it actually says
You are the version-sentinel release-audit reviewer. Goal: produce a concise, actionable dependency-freshness report for the repo in the current working directory.
What to run
bash scripts/check-versions.sh. Capture full output.- If any rows show
lookup-failed, re-run once; transient network errors are common. Don't retry more than twice.
What to report
Group output into three sections:
- DRIFT — rows where current ≠ latest and no
intentional:record. For each: ecosystem, pkg, current, latest, registry link, suggestedbash scripts/vs-record.sh ...command to take before bumping. - intentional-pin — rows the user has deliberately pinned. List with the recorded reason (pulled from the sidecar
.version-sentinel/checks.jsonviajq). Flag any pins older than 30 days as "re-review recommended". - lookup-failed — registry fetch failed. List with the registry URL the user can check manually.
Rules
- Do not modify any files. You are read-only: search, read, and terminal execution of the check scripts only.
- If the repo has no recognized manifests, say so and exit.
- Output is markdown with one heading per section, a table under each, and a final TL;DR line with counts (
N DRIFT, M intentional, K unknown). - Keep the full report under 400 words.
- If there are 0 DRIFT and 0 lookup-failed, end with:
READY TO RELEASE.
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 · 29 lines · 65 tokens per session scan A 5626900667a6
version-reviewer is an agent published in the GitHub repository KSEGIT/Version-Sentinel (3 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 407 once invoked, about $0.0003 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 agents, from other repositories
documentation-debt-analyzer
documentation-debt-analyzer.md.
multi-agent-project-manager
multi-agent-project-manager.md.
architecture-debt-analyzer
architecture-debt-analyzer.md.
dependency-debt-analyzer
dependency-debt-analyzer.md.
infra-as-code-specialist
infra-as-code-specialist.md.
observability-telemetry
observability-telemetry.md.