What is deepiri-sorge?

A GitHub pull-request review bot that runs through GitHub Actions and can be triggered with the `/sorge` comment.

Use it to add Sorge to a repository, configure its workflow and settings, trigger reviews, and interpret or address its comments.

It gives a first pass over proposed code changes and points out possible problems before merging, so reviewers do not have to start from a blank page.

deepiri-sorge — Skill for Claude Code and Codex by Team-Deepiri

Install

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.

Any agent

npx skills add Team-Deepiri/deepiri-axiom --skill deepiri-sorge

Clone the repo

git clone --depth 1 https://github.com/Team-Deepiri/deepiri-axiom

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/deepiri-sorge/github.svg)](https://agentmods.dev/skills/team-deepiri/deepiri-axiom/deepiri-sorge)

Your own site

<a href="https://agentmods.dev/skills/team-deepiri/deepiri-axiom/deepiri-sorge"><img src="https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/deepiri-sorge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/team-deepiri/deepiri-axiom/deepiri-sorge"><img src="https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/deepiri-sorge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 689 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.00055	$0.00689
Opus 5	$0.00028	$0.00345
Sonnet 5	$0.00011	$0.00138
Haiku 4.5	$0.00006	$0.00069

Measured 11d ago against content hash ec0f9cad36f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

deepiri-sorge 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 11d 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.

skills/deepiri-sorge/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deepiri Sorge

Repo: deepiri-sorge — distributed AI PR review bot (GitHub Actions + optional Gemini/GitHub Models).

When to use this skill

Opening or updating a PR that needs a first-pass AI review
Wiring Sorge into a Deepiri repo (workflow + config + secrets)
Interpreting Sorge comments or skip messages
User says /sorge, "sorge", or "AI PR review"

Trigger a review (`/sorge`)

Ensure the PR exists and is pushed to GitHub.
Comment /sorge on the PR (issue comment body is exactly /sorge, optionally with a short note after).
Treat the bot reply as a first pass that informs — not replaces — manual review.
Fold Blocking / Important findings into the human review; do not merge on Sorge alone.

Also auto-runs on pull_request opened/synchronize/reopened (and configurable push) when the reusable workflow is installed.

Agent checklist (ship a PR)

Push branch; open PR against main or dev as repo policy requires
Comment /sorge on the PR
Wait for the review comment (or skip notice)
Address real issues; re-comment /sorge after large follow-up pushes if needed
Complete human/CI review gates before merge

Install into a repo

Add .github/workflows/pr_review.yml calling the Sorge workflow (see deepiri-sorge README), or copy the workflow from that repo.
Optional root sorge.toml — defaults are fine for most repos.
Repo secret GOOGLE_API_KEY (Gemini) when using Gemini routing; GITHUB_TOKEN is provided by Actions.
Align with branch protection — Sorge comments are advisory unless the team explicitly requires a Sorge check.

Minimal `sorge.toml`

[sorge]
enabled = true

[filters]
min_lines = 20
skip_docs = true
skip_deps = true

[review]
style = "concise"
include_security = true
include_performance = true

Local dry-run (no PR comment)

cd deepiri-sorge   # or sibling clone from .axiom/ecosystem.json
poetry install     # or pip install -r requirements.txt
git -C <target-repo> diff origin/main...HEAD > /tmp/pr.diff
python -m bot.main --diff /tmp/pr.diff --dry-run --verbose

Read the full file on GitHub · 66 lines

Changes

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.

11d ago First seen · 66 lines · 55 tokens per session scan A ec0f9cad36f3

Subscribe to this mod's changes

deepiri-sorge is a skill published in the GitHub repository Team-Deepiri/deepiri-axiom (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 55 tokens to every session and 689 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.

CI and CD Code review DevOps and cloud

gemini-review

Google Gemini CLI code review with Gemini 2.5 Pro, 1M token context, CI/CD integration.

alinaqi/maggy · 26 tokens

squid-implement-night

Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the human a validated, ready-to-squash-merge PR. Trigger after /squid-plan.

iusztinpaul/squid · 52 tokens

pr-babysitter

Monitors or repairs an open GitHub PR: CI failures, conflicts, review threads, and merge readiness, reporting state changes. Use when asked to "watch this PR", "fix CI", "resolve conflicts", or "address review comments". For PR metadata use pr-creator; for npm release PRs use autoship.

mblode/agent-skills · 72 tokens

tech-debt-ci-review

Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.

ZaxbyHub/opencode-swarm · 61 tokens

aster-review-ci

Run aster code reviews non-interactively in CI, GitHub Actions, or from another agent. Covers aster review --pr, --json, --stream, --comment, diff-from-stdin, token handling, and filtering findings. Use when wiring aster into a pipeline, posting PR comments, or parsing review output programmatically.

Zfinix/aster · 75 tokens

review

Review before merge. Stage-1 spec-compliance gate, then risk-selected Stage-2 review axes from the canonical set. analyst always runs, callers can pin extra always-on axes, and explicit deep review runs the full 16-axis set. Run after /test. Do NOT invoke code-qualities-assessment, doc-accuracy, golden-principles, or…

rjmurillo/ai-agents · 97 tokens