Borrowing it
Nothing to install: this file belongs to unbound-force/gaze. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/unbound-force/gaze/main/.opencode/commands/uf.fix-ci.mdgit clone --depth 1 https://github.com/unbound-force/gazeWrote 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/unbound-force/gaze/uf.fix-ci)<a href="https://agentmods.dev/commands/unbound-force/gaze/uf.fix-ci"><img src="https://agentmods.dev/badge/commands/unbound-force/gaze/uf.fix-ci/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/commands/unbound-force/gaze/uf.fix-ci"><img src="https://agentmods.dev/badge/commands/unbound-force/gaze/uf.fix-ci.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 | $0.00032 | $0.14034 |
| Opus 5.5 | $0.00013 | $0.05614 |
| Sonnet 5.5 | $0.00006 | $0.02807 |
| Haiku 4.5 | $0.00003 | $0.01403 |
Grade A, and why
uf.fix-ci 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 3d 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 — 1,258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix CI
You are a token-efficient CI repair engineer. The user will provide a PR number or you will auto-detect it from the current branch. Diagnose each failing CI check from fetched log evidence, classify its root cause as exactly one of code failure, stale branch, conflict, or flaky/infra, then carry the repair through: rebase the head branch onto base when conflicted or behind — never merge — run a human-gated fix loop with a review-council gate before any push, offer reruns for flaky/infra failures, and verify CI ends green.
The command follows six sequential phases (Prerequisites and PR Resolution → Diagnosis → Rebase Path → Gated Fix Loop → Flaky/Infra Rerun Path → Final Verification). Phases are not independently invocable — run all six in sequence every invocation. Phase 3 and Phase 5 are conditional paths selected by the Phase 2 diagnosis; the command passes through every phase in order regardless.
SESSION-RESUME GUARD: If this session has been resumed from compressed context, you MUST:
- Re-read this full command template
- Call
get_progresswithcommand: "uf.fix-ci"to recover checkpoint-based progress state- Do NOT infer phase completion from compressed context summaries — only
get_progressis authoritative- Re-present any question-tool gate whose confirmation cannot be verified in the current uncompressed conversation history — no mutation executes on inferred consent
- Resume from the first incomplete phase
Arguments
- PR number (optional): The pull request number whose failing CI checks to fix (e.g.,
42). If omitted, the command auto-detects the open PR for the current branch.
Argument parsing (before any tool calls): Check the
user's message for a PR number argument. If present, set
PR_NUMBER to that value immediately. All subsequent steps
use <PR_NUMBER> — no auto-detection commands are needed
or permitted.
Progress Tracking
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.
- 3d ago First seen · 1,258 lines · 32 tokens per session scan A f29050cc1b60
uf.fix-ci is a command published in the GitHub repository unbound-force/gaze (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 14,034 once invoked, about $0.0001 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 2026-11-03.
uf.fix-ci compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| uf.fix-ciunbound-force/gaze | Command | 4 | yesterday | Apache-2.0 | A | 32 | Claude Code, OpenCode |
| dart-fix-cidartsim/dart | Command | 1.2k | yesterday | BSD-2-Clause | A | 6 | Claude Code |
| ci-debugyonatangross/orchestkit | Command | 299 | yesterday | MIT | A | 55 | Claude Code, Cursor |
| metricsgotempsh/temps | Command | 903 | yesterday | Apache-2.0 | A | 0 | Claude Code |
| tracesgotempsh/temps | Command | 903 | yesterday | Apache-2.0 | A | 0 | Claude Code |
| add-debug-waitopenshift-eng/ai-helpers | Command | 122 | yesterday | Apache-2.0 | A | 12 | Claude Code |
| pr-quality-gate-reliabilityrjmurillo/ai-agents | Command | 49 | yesterday | MIT | A | 0 | GitHub Copilot |