Borrowing it
Nothing to install: this file belongs to duckduckgo/apple-browsers. 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/duckduckgo/apple-browsers/main/.claude/skills/ddg-diagnose-ci-failure/SKILL.mdgit clone --depth 1 https://github.com/duckduckgo/apple-browsersWrote 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/duckduckgo/apple-browsers/ddg-diagnose-ci-failure)<a href="https://agentmods.dev/skills/duckduckgo/apple-browsers/ddg-diagnose-ci-failure"><img src="https://agentmods.dev/badge/skills/duckduckgo/apple-browsers/ddg-diagnose-ci-failure/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/duckduckgo/apple-browsers/ddg-diagnose-ci-failure"><img src="https://agentmods.dev/badge/skills/duckduckgo/apple-browsers/ddg-diagnose-ci-failure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 287 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00000 | $0.04066 |
| Opus 5 | $0.00000 | $0.02033 |
| Sonnet 5 | $0.00000 | $0.00813 |
| Haiku 4.5 | $0.00000 | $0.00407 |
Grade A, and why
ddg-diagnose-ci-failure scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
If `gh` is not installed, stop and tell the user to install it (`brew install gh` on macOS) - do not attempt to substitute `curl` against the GitHub API. If `gh` is installed but not authenticated, stop and tell the user How it starts
The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose CI Failure
Investigate a GitHub Actions workflow failure, classify it, trace test failures back to the local code, and propose a fix.
Prerequisites
This skill requires the GitHub CLI (gh) to be installed and authenticated. Before doing anything else, run:
command -v gh >/dev/null && gh auth status
If gh is not installed, stop and tell the user to install it (brew install gh on macOS) - do not attempt to substitute curl against the GitHub API. If gh is installed but not authenticated, stop and tell the user to run gh auth login. Either way, bail out before resolving inputs.
Inputs
The skill resolves any of the following to a single GitHub Actions run to investigate. gh autodetects the repo from the current working directory's git remote, so you don't need to pass --repo unless the user supplies a URL pointing at a different repo - in which case extract <owner>/<repo> from the URL and pass it explicitly with --repo <owner>/<repo>. Resolve the input first, then start at Step 1 with the resulting run_id and any optional job_id or attempt_number.
Actions run URL
Example: https://github.com/<owner>/<repo>/actions/runs/25519433222 (optionally with /job/<id> or /attempts/N).
Extract run_id, job_id if present, and attempt_number if the URL includes /attempts/N. Use directly. Do not discard the attempt number: all later gh run view commands for this run must include --attempt {attempt_number} so logs and status match the supplied attempt instead of defaulting to the latest attempt.
PR URL
Example: https://github.com/<owner>/<repo>/pull/4752.
Extract the PR number, then resolve as below.
Bare PR number
Example: 4752 or #4752.
gh pr checks <pr_number> --json name,state,link,workflow
Pick the most recent failed check's run URL. If multiple checks failed, prefer the broadest test workflow over lint-only or build-only ones (in the apple-browsers monorepo that's iOS - PR Checks, macOS - PR Checks, DBP - PR Checks).
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.
- 10d ago First seen · 293 lines · 0 tokens per session scan A 9b452e769fc3
ddg-diagnose-ci-failure is a skill published in the GitHub repository duckduckgo/apple-browsers (252 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,066 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other skills, from other repositories
github-ci-fix
Use when PR checks fail, CI is red, or GitHub Actions workflows break - systematically inspects failing checks via gh CLI, pulls logs, checks for flakiness and scopes the breaking commit, scopes external checks, then creates fix plan using existing plan skill.
ipad-layout-audit
Detects hardcoded iPhone-sized widths, missing iPad orientation keys, and absent size-class adaptation that cause layout failures on iPad reviewers' devices under guidelines 2.1 and 2.4.1.
crash-risk-audit
Detects force unwraps, force casts, force try, and other crash-prone Swift patterns that can cause unrecoverable crashes during App Store review, violating Guideline 2.1.
operating-github-ci-fixer
Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.
argent-react-native-optimization
Optimizes a React Native app by profiling first to find real bottlenecks, then sweeping for mechanical issues. Entry-point for all performance work. Use when the app feels slow, user asks to optimize, fix re-renders, reduce jank, or improve startup. Delegates to argent-react-native-profiler for measurement.
meta-long-running-build-watchdog
Watches a long-running command via tmux, lets sub-agent diagnose failures and propose a fix, and records the diagnosis to memory. Designed for overnight model fine-tunes, CI image builds, or repeated regression suites that may fail intermittently.