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 skills add dgk-dev/dgk-gpt --skill rrgit clone --depth 1 https://github.com/dgk-dev/dgk-gptWrote 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/skills/dgk-dev/dgk-gpt/rr)<a href="https://agentmods.dev/skills/dgk-dev/dgk-gpt/rr"><img src="https://agentmods.dev/badge/skills/dgk-dev/dgk-gpt/rr/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.
<a href="https://agentmods.dev/skills/dgk-dev/dgk-gpt/rr"><img src="https://agentmods.dev/badge/skills/dgk-dev/dgk-gpt/rr.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00051 | $0.00643 |
| Opus 5.5 | $0.00020 | $0.00257 |
| Sonnet 5.5 | $0.00010 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
rr 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 1mo 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/rr
Use glm-review as a second reviewer for the current change set, then validate the reported issues against the actual code before you trust or repeat them.
Default Flow
- Determine the exact change scope first.
- If the user points to a commit, prefer commit mode.
- If the user says
staged, use staged mode. - If the user says
pr, use PR mode. - If the workspace has mixed unrelated changes, build a focused diff file for only the intended files.
- Run a quick connectivity check only when the environment looks suspect:
glm-review --health
- Run the review with the narrowest correct input:
glm-review
glm-review --mode staged
glm-review --mode pr
glm-review --mode commit --ref <COMMIT_HASH>
glm-review --diff-file /tmp/glm-review-diff.patch
- Treat the output as a candidate issue list, not ground truth.
- Re-open the referenced code and verify each claim.
- Report only valid issues, ordered by severity.
- If fixing issues is in scope, fix them and rerun the closest relevant verification.
Choosing Review Input
Prefer the most specific path that isolates the current task:
- committed single change:
glm-review --mode commit --ref <COMMIT_HASH>
- committed subset of files:
glm-review --mode commit --ref <COMMIT_HASH> --files src/a.ts src/b.ts
- custom focused diff for multi-session or mixed worktrees:
GIT_ROOT=$(git rev-parse --show-toplevel)
cd "$GIT_ROOT" && git diff HEAD -- <file1> <file2> ... > /tmp/glm-review-diff.patch
glm-review --diff-file /tmp/glm-review-diff.patch
If the diff is empty, stop and say there is nothing to review.
Validation Rules
- Do not parrot
glm-reviewoutput without checking the code. - Drop false positives explicitly instead of forwarding them.
- Distinguish between confirmed bugs, arguable style comments, and already-fixed issues.
- If the review claims a regression, inspect the relevant file and the actual diff before accepting it.
Error Handling
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.
- 1mo ago First seen · 90 lines · 51 tokens per session scan A c56a7d1b2248
rr is a skill published in the GitHub repository dgk-dev/dgk-gpt (55 stars, last pushed 7mo ago), licensed MIT. It adds 51 tokens to every session and 643 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
code-review
You are a senior code reviewer. You receive diffs via stdin.
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
agent-debug-ci
Investigate failed scheduled or nightly GitHub Actions runs on the default branch, determine whether the failure is reproducible and repository-owned, implement the smallest evidence-backed fix, validate it, and open a pull request. Use when a failed nightly CI event starts an agent, or when the standard CI or…
audit-ci
Run and analyze Elements cold CI performance profiles and propose evidence-backed build, test, lint, and dependency-graph improvements. Use whenever asked to profile or benchmark pnpm run ci, rerun ci:profile, create a CI performance audit, compare CI timings, find bottlenecks or the completion path, investigate a CI…