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 agentmods add skills/lastrada/claude/pr-tasklistnpx skills add LaStrada/claude --skill pr-tasklistgit clone --depth 1 https://github.com/LaStrada/claudeWrote 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/lastrada/claude/pr-tasklist)<a href="https://agentmods.dev/skills/lastrada/claude/pr-tasklist"><img src="https://agentmods.dev/badge/skills/lastrada/claude/pr-tasklist.svg" alt="Measured on agentmods" 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 | $0.00173 | $0.06636 |
| Opus 5 | $0.00086 | $0.03318 |
| Sonnet 5 | $0.00035 | $0.01327 |
| Haiku 4.5 | $0.00017 | $0.00664 |
Grade C, and why
pr-tasklist scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
trap 'rm -rf "$tmpdir"' EXIT How it starts
The opening of the file, as written. The whole thing — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pr-tasklist
A cross-repo dashboard for the PRs the user cares about. Lives in four sections:
- Mine — PRs the user authored.
- Assigned — PRs the user is assigned to.
- Review-requested — PRs where the user is a requested reviewer.
- Followed — user-curated list, persisted in a storage backend.
The first three are live reads via the GitHub MCP server (preferred) or gh api graphql (fallback). The fourth requires a storage backend (local JSON or secret Gist), set up on first run.
When this applies
Trigger phrases (not exhaustive):
- "show my PRs" / "my PR list" / "my open PRs" / "PR list"
- "PR dashboard" / "PR queue" / "PR tasklist"
- "what's on my plate" (in a dev context)
- "what should I review" / "what PRs are waiting on me"
- The user runs
/prs(any subcommand:setup,reconfigure,unfollow, etc.).
Do NOT trigger for:
- Reviewing a single PR (use
code-review,review, orpr-review-toolkit:review-pr). - Creating a PR (use the standard PR-creation flow).
- Managing issues, notifications, or discussions — out of scope.
- Querying non-github.com hosts (Gitea, Forgejo, GitLab on prem, etc.) —
ghonly.
Hard constraints
- Read-only by default. Show the dashboard. Mutate state only on explicit user pick.
- Don't post comments, approve, request changes, or merge from this skill. Open-in-browser is the only outbound action.
- Confirm before any first-time gist creation. Never silently create a public artifact in the user's account.
- Show storage location whenever it changes. When following/unfollowing, end with a single line confirming where the state was persisted (path or gist URL).
- Never store API tokens. Rely entirely on
ghCLI auth. - Never hardcode usernames or orgs. This plugin is public; users come from any GitHub account.
- Surface auth/setup failures loudly. Don't paper over a missing
gh auth statuswith an empty dashboard.
Steps
1. Detect backend + preflight
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 · 495 lines · 173 tokens per session scan C a63c7d01f48c
pr-tasklist is a skill published in the GitHub repository LaStrada/claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 173 tokens to every session and 6,636 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…