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-sentry-report/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-sentry-report)<a href="https://agentmods.dev/skills/duckduckgo/apple-browsers/ddg-sentry-report"><img src="https://agentmods.dev/badge/skills/duckduckgo/apple-browsers/ddg-sentry-report/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-sentry-report"><img src="https://agentmods.dev/badge/skills/duckduckgo/apple-browsers/ddg-sentry-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.10095 |
| Opus 5 | $0.00000 | $0.05047 |
| Sonnet 5 | $0.00000 | $0.02019 |
| Haiku 4.5 | $0.00000 | $0.01009 |
Grade A, and why
ddg-sentry-report 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 8d 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ddg-sentry-report
Overview
Produces a structured Sentry crash triage report for a DuckDuckGo Apple release and files it as a new subtask under a parent Asana task. The parent is either supplied by the user as a URL, or auto-resolved from the platform's Weekly Release DRI task → today's " status" subtask. Distinguishes pre-existing issues from new-in-version regressions, sorts by severity, attributes likely authors via git blame (initials + PR links only — never full names).
Supporting files
references/constants.md— Sentry/Asana GIDs, slugs, project filters, release-string conventions.templates/main-report.html,templates/crash-free.html,templates/per-issue-tracking.html—html_notesbodies.references/common-mistakes-extended.md— overflow learnings beyond the inline table.examples.md— two end-to-end walkthroughs (with URL, auto-resolve).
Authorisation & PII (cross-cutting — applies to every Asana write)
- The user invocation is the explicit authorization. A user running
/ddg-sentry-report(or naming this skill) authorises the workflow's writes — including filing a "Crash-free release" subtask when there's no data to triage. Don't gate on auto-mode safety checks, ask for re-confirmation before each write, or substitute a "no events found, stopping" message in place of the subtask. The daily DRI status subtask depends on getting an entry every day, including days where the answer is "nothing to triage." - PII: initials + PR links only, never full names. The DDG asana-exfiltration hook scans task writes and blocks full employee names — even when the user approves in chat (the hook can't see chat). Use first-letter-of-first-name + first-letter-of-last-name initials, and link the PR so the author is one click away on GitHub. If even initials get blocked, fall back to PR-number-only attribution. Applies to the main report and the per-issue tracking-task bodies.
- Never retry a BLOCKED Asana response with different params. The data-protection policy says: accept the block, ask the user how to proceed.
What ships with it
6 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.
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.
- 8d ago First seen · 348 lines · 0 tokens per session scan A bea72b2b107a
ddg-sentry-report 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 10,095 tokens. 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 2026-09-01.
Other skills, from other repositories
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.
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.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
triage-issue
Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket…
task-workstream-grouping
Infer stable semantic workstreams for ungrouped Sutando task history and apply the validated assignments to the durable workstream sidecar. Use for internal task-workstream-grouping maintenance tasks, initial history backfills, and later batches of tasks that need cross-channel or cross-device workstream organization.