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-apple-feedback-review/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-apple-feedback-review)<a href="https://agentmods.dev/skills/duckduckgo/apple-browsers/ddg-apple-feedback-review"><img src="https://agentmods.dev/badge/skills/duckduckgo/apple-browsers/ddg-apple-feedback-review/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-apple-feedback-review"><img src="https://agentmods.dev/badge/skills/duckduckgo/apple-browsers/ddg-apple-feedback-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Rogue Agent · line 484 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 655 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 | $0.00070 | $0.09070 |
| Opus 5 | $0.00035 | $0.04535 |
| Sonnet 5 | $0.00014 | $0.01814 |
| Haiku 4.5 | $0.00007 | $0.00907 |
Grade A, and why
ddg-apple-feedback-review 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 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.
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 — 721 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Feedback Review
Overview
Apple-side feedback is fragmented across five Asana projects (in-app feedback, Privacy Pro feature requests, Privacy Pro issues, internal product feedback, and App Store reviews) and split between iOS and macOS. This skill fetches all relevant sources, deduplicates by task GID, clusters reports into named issue groups, and presents a per-platform summary with a separate App Store reviews section. The output is a one-shot snapshot, not a query interface.
Sensitive data halt: An organization-level instruction requires you to
stop and surface a ⚠️ SENSITIVE DATA warning if any task surfaced by this
skill contains legal (SILO, ACP, attorney-client privilege), HR
(performance, compensation, terminations, PIPs), finance (M&A, budget
details), or security (audits, incidents) content. List the triggers and
ask for explicit confirmation before continuing - do not include such tasks
in the report unsolicited.
When NOT to use
- Alerting or monitoring (this is a snapshot, not a watcher).
- Individual task triage (use Asana directly).
- Anything that needs a feedback database or repeated queries against the same window (the skill re-fetches from Asana every time).
Lethal trifecta note
This skill accesses Asana, an internal data source. A session-level hook blocks WebFetch and most non-allowlisted MCP tools for the rest of the session once Asana is touched. If the user needs WebFetch, Slack, or other non-allowlisted tools afterwards, run this skill in a separate session.
The hook in this environment is also stricter about Bash: once Asana
has been touched, Bash calls that look like they're "preparing report
content to post back" are denied, including python3, jq, and rm on
scratch files. This skill is therefore designed to run without Bash
post-Asana - all task data stays in tool-call context, the report HTML
is built in-message, and there are no scratch files to clean up.
Parameters
This skill accepts optional arguments. Parse them from the free-text args string passed to the skill.
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 · 721 lines · 70 tokens per session scan A abe34b87ad82
ddg-apple-feedback-review is a skill published in the GitHub repository duckduckgo/apple-browsers (252 stars, last pushed yesterday), licensed Apache-2.0. It adds 70 tokens to every session and 9,070 once invoked, about $0.0003 per session on Opus 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 2026-09-01.
Other skills, from other repositories
linear-app-setup
Create and configure a Linear agent app so the assistant can manage issues, projects, and workflows under its own identity.
benchmark
Run performance + quality benchmarks. ASR reports WER, RTF, process memory, and throughput across engines/variants. Arguments include asr, tts, vad, diarize, asr-quick.
review-pr
Review a pull request for conceptual fit, architecture impact, adversarial failure modes, security risk, docs impact, regression risk, test coverage, and merge readiness. Use when asked to review a PR, check whether a PR is safe to merge, decide if more tests are needed, perform adversarial or security review, or…
factory-mcp
Use the Warp Factory MCP to hand work to a software factory and collaborate with it — bundle local work and send it to the cloud, find factory tasks from a Slack thread / Linear ticket / description, and pull a task down to test or iterate locally and hand it back.
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.
cross-squad
Coordinating work across multiple Squad instances.