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/varienos/agentic-workflow/auto-review.skeletongit clone --depth 1 https://github.com/varienos/agentic-workflowWrote 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/varienos/agentic-workflow/auto-review.skeleton)<a href="https://agentmods.dev/commands/varienos/agentic-workflow/auto-review.skeleton"><img src="https://agentmods.dev/badge/commands/varienos/agentic-workflow/auto-review.skeleton.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 | $0.00000 | $0.03038 |
| Opus 5 | $0.00000 | $0.01519 |
| Sonnet 5 | $0.00000 | $0.00608 |
| Haiku 4.5 | $0.00000 | $0.00304 |
Grade A, and why
auto-review.skeleton scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Review - Loop Uyumlu Diff Review
Son review hash'ini izler, yeni diff varsa shallow review yapar, MINOR bulgulari dogrudan duzeltir, MAJOR bulgular icin backlog task acar. Kullanim:
/auto-review,/auto-review <commit_hash>,/auto-review HEAD~3..HEAD
Step 1 - Diff ve State Tespiti
1.1 - Arguman Cozumleme
| Girdi | Davranis |
|---|---|
| Bos | Son commit: cd ../Codebase && git diff HEAD~1..HEAD |
| Commit hash | Belirtilen commit: cd ../Codebase && git show <hash> |
| Range | Aralik: cd ../Codebase && git diff <range> |
1.2 - Normalize Diff Cikar
Review edilecek diff'i deterministik sekilde cikar:
cd ../Codebase && git diff --no-ext-diff --minimal <range_veya_default>
Bu diff'ten su bilgileri cikar:
- Degisen dosya listesi
- Eklenen/silinen satir sayilari
- Degisiklik tipi (fix, refactor, test, config)
KURAL: Diff bossa veya sadece whitespace degisikligi varsa "Incelenecek yeni degisiklik yok" deyip DUR.
1.3 - Hash Hesapla
Diff hash'ini stabil sekilde hesapla:
CURRENT_DIFF_HASH=$(cd ../Codebase && git diff --no-ext-diff --minimal <range_veya_default> | shasum -a 256 | awk '{print $1}')
CURRENT_HEAD=$(cd ../Codebase && git rev-parse HEAD)
1.4 - State Dosyasini Yukle
.claude/tracking/auto-review-state.json dosyasini kullan:
{
"last_reviewed_hash": null,
"last_review_target": null,
"last_reviewed_head": null,
"last_reviewed_at": null,
"last_fix_commit": null,
"last_report_path": null
}
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 · 296 lines · 0 tokens per session scan A 89af3759f30d
auto-review.skeleton is a command published in the GitHub repository varienos/agentic-workflow (58 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,038 tokens. 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 2026-08-30.
Other commands, from other repositories
feature
Create a feature specification using spec-driven development.
adr
You are helping create a new ADR (Architecture Decision Record). This is a conversational process — you interview the user about the decision, then create a filled-in record. ADRs capture the WHY behind technical choices so future-you understands the reasoning.
triage-issues
Launch the Issue Triage Agent (Haiku) to categorize and prioritize GitHub issues.
integrate
/forge:integrate is the integration assistant for connecting your project to external services. It covers version control (GitHub, GitLab), monitoring (Sentry, Datadog), communication (Slack, Discord), databases (PostgreSQL, Redis, MongoDB), and cloud platforms (AWS, GCP, Vercel, Netlify). For each service, it checks…
fix-issue
!gh issue view $ARGUMENTS 2>/dev/null || echo "Could not fetch issue $ARGUMENTS".
rev
Invoke Code Reviewer for code quality, security, requirements validation, and best practices review.