← ClaudeAtlas

biweekly-codeql-community-pulselisted

Biweekly scheduled agent. Surveys the github/codeql repo + community packs for new queries, modified queries, and new packs published in the past 14 days. Relevance-scores each against the org's stack (using daily-cve-digest's stack.yml as the source of in-scope ecosystems) — surface only ecosystem-matching results. Output at vault/digests/biweekly/YYYY-MM-DD-codeql-community-pulse.md. Feeds the codeql-pattern-finder skill — every relevant new community query is a candidate for the org's adoption queue. Use when the user asks to run the CodeQL community pulse or see what new community queries or packs shipped upstream — and on its biweekly schedule.
themarmack/research-bot · ★ 0 · AI & Automation · score 68
Install: claude install-skill themarmack/research-bot
# biweekly-codeql-community-pulse The CodeQL upstream watch. Every two weeks, surfaces new community work that's worth evaluating for the org's CodeQL pack rollout. Composes with `codeql-pattern-finder` (which evaluates specific queries for adoption) and `codeql-onboarding-helper` (which deploys adopted queries). ## Agent config (consumed by `scheduled-agent-runner`) ```yaml agent_name: biweekly-codeql-community-pulse cadence: biweekly schedule_hint: "every other Tuesday 08:00 local" source_filter: custom: codeql-community sources: - https://github.com/github/codeql/commits/main.atom - https://github.com/codeql-packs # community packs org stack_match_config: ../daily-cve-digest/stack.yml # filter to in-scope ecosystems only max_items: 30 verify_loadbearing: false # community queries are evaluated, not "verified" as facts curate_findings: false # adoption decisions go through codeql-pattern-finder, not memory-curator digest_template_overrides: template: codeql-community-pulse why_you_care_extra: | Per item: 1. Which in-scope ecosystem does this target? 2. Is the query syntactic (cheap, easy to deploy) or taint-tracking (expensive, needs tuning)? 3. What's the closest existing match in the org's current suite, and is this duplicative? 4. Estimated effort to evaluate-for-adoption (S / M / L). ``` ## Sections per item For each surfaced query: 1. **Title** + repo path + author. 2. **Targets**: language + ecosystem from `stack.y