Blog
News, launch notes, guides, and comparisons for builders exploring reusable AI agent skills, trust signals, and ecosystem shifts.
Latest posts
Follow product updates, editorial pieces, and practical explainers that help users navigate the marketplace and adjacent agent ecosystems.
-
Sign agent-made Git commits with gitsign
Apply keyless Sigstore-backed signatures to Git commits so automated changes retain verifiable provenance.
-
Generate SLSA build provenance in GitHub Actions
Attach signed SLSA provenance to GitHub Actions builds so release artifacts ship with verifiable supply-chain metadata.
-
Audit Go dependency licenses with go-licenses
Produce a license inventory for Go module dependencies before release, procurement review, or open-source due diligence.
-
Debug live Chromium sessions with browser-debugger-cli
Pull DOM, console, network, and CDP telemetry from a live Chromium session when an agent needs to debug a failing browser task.
-
Apply site-specific action manuals with Actionbook
Load maintained action manuals for fragile websites so agents can execute known flows more reliably than generic browser prompting.
-
Monitor coding-agent token spend with Splitrail
Track token burn, spend, and model mix across multiple coding-agent tools from one local monitoring workflow.
-
Inspect agent model traffic with LLMTrace
Proxy OpenAI-compatible model traffic so operators can inspect prompts, detect risks, and enforce budget or policy controls.
-
Generate and safely patch AGENTS.md and RUNBOOK.md with AGENTS.md Generator
Bootstrap and safely update AGENTS.md and RUNBOOK.md without clobbering hand-edited docs, so coding-agent repos keep a clean machine-readable contract.
-
Dispatch coding agents from GitHub issue labels and return pull requests with Patchwork Agents
Use issue labels as a lightweight dispatch layer that fans repository work out to Claude Code, Codex, or Aider workers and brings back PRs.
-
Regression test LLM apps and agents with metrics, traces, and eval suites using DeepEval
Run repeatable eval suites against prompts, RAG pipelines, and agents so regressions surface before release.