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 nexiouscaliver/OmniForge --skill omnicheck-gitlabgit clone --depth 1 https://github.com/nexiouscaliver/OmniForgeWrote 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/nexiouscaliver/omniforge/omnicheck-gitlab)<a href="https://agentmods.dev/skills/nexiouscaliver/omniforge/omnicheck-gitlab"><img src="https://agentmods.dev/badge/skills/nexiouscaliver/omniforge/omnicheck-gitlab/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/nexiouscaliver/omniforge/omnicheck-gitlab"><img src="https://agentmods.dev/badge/skills/nexiouscaliver/omniforge/omnicheck-gitlab.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 | $0.00041 | $0.03929 |
| Opus 5.5 | $0.00016 | $0.01572 |
| Sonnet 5.5 | $0.00008 | $0.00786 |
| Haiku 4.5 | $0.00004 | $0.00393 |
Grade A, and why
omnicheck-gitlab 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 — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OmniCheck
Verify whether requested MR changes have been applied — diff analysis + targeted nudge comments.
Check all discussion threads on a GitLab MR against the current diff. Resolved threads are marked APPLIED. Unresolved threads are analyzed by a subagent to determine if the fix was applied silently or not at all. Unaddressed threads receive nudge replies and a summary comment. When every finding is verified applied, offer to approve the MR (as the OmniCheck bot when OMNICHECK_BOT_TOKEN is set).
Core principle: Thread status check + diff analysis + user approval gate = accurate, non-spammy follow-up — and, when clean, a one-keystroke approval.
Announce at start: "I'm using OmniCheck to verify findings on MR !{id}."
Prerequisites
glabCLI authenticated (glab auth statusto verify)- Git repository with remote pointing to GitLab
- Current working directory is in the git repo
- MR must have discussion threads
Input Parsing
Accept any of: MR number (136), prefixed (!136), or full GitLab URL.
Extract MR ID. If URL provided, extract project path and MR IID.
The Process
Phase 1: GATHER — fetch all threads + MR diff/data
Phase 2: ANALYZE — single subagent checks each open thread against the diff
Phase 3: REPORT — present status table, then branch:
Branch A (unaddressed findings): user approves nudge list
Branch B (all verified): "Approve MR? [Y/n]"
Phase 4: ACT — Branch A: reply on each NOT_APPLIED thread + summary comment
Branch B: approve_mr() + summary comment
Phase 5: DONE — no cleanup needed (no worktrees)
Auto-approval (Branch B) is OFF by default. It only appears when
NOT_APPLIED + NEEDS_HUMAN = 0, and only fires if the user answers Y. WhenOMNICHECK_BOT_TOKENis set,approve_mrapproves as the bot so it can clear the gate even when "Prevent approval by creator/committer" blocks the human user. See the setup guide.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/analysis-agent-prompt.md 3.9 KB
- references/nudge-guide.md 3.5 KB
- references/replay-table-2026-09-11.md 5.1 KB
- references/sweep-prompt.md 2.7 KB
- references/verdict-model.md 6.4 KB
- scripts/omni_sweep.py 47 KB runs code
- scripts/omni_verdict.py 14 KB runs code
- scripts/replay_audit.py 13 KB runs code
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 Changed · +48 lines a13a073c948d
- 1mo ago First seen · 318 lines · 41 tokens per session scan A 82c8c2a4f701
omnicheck-gitlab is a skill published in the GitHub repository nexiouscaliver/OmniForge (4 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 3,929 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 2026-08-31.
Other skills, from other repositories
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
triage
Triage review findings interactively — approve, skip, or prioritize each issue. Use after /phx:review to filter findings before fixing.
refactoring-patterns
Apply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code smells", "extract method", "replace conditional", "technical debt", "move method", "inline variable", "decompose conditional", or "clean up this messy code". Also trigger when…
techdebt
Analyze Elixir/Phoenix technical debt — duplicates, refactoring opportunities, credo issues. Use when asked about code quality, cleanup, or what to improve.
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).