skills/agentedit-cli/SKILL.md
Apply deterministic targeted file edits with the local `agentedit` CLI. Use when an agent needs exact-match replacements, anchored inserts, line-range updates, or whole-file writes from a JSON or YAML edit spec.
npx skillsauth add sebastianboehler/agent-cli-utils agentedit-cliInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use agentedit for safe, targeted file changes. Prefer it over broad patch parsing when the caller can describe edits as explicit replacements, inserts, line-range updates, appends, or writes.
Prefer the installed binary when it exists:
agentedit -spec edits.yaml
If working inside this repository or the binary is not installed, run:
go run ./cmd/agentedit -- -spec edits.yaml
replace for one exact old-to-new substitution.replace with replace_all: true only when every match should change.insert_before or insert_after with one exact anchor.replace_lines for deterministic line-range rewrites.append to add content at the end of a file.write for full-file replacement or creation.-fail-on-noop=true so missed matches fail loudly.-dry-run first when the edit target may have drifted.create: true only when the task really intends to create a file.edits:
- path: README.md
action: replace
old: "Small Go CLIs"
new: "Small, deterministic Go CLIs"
- path: config.toml
action: insert_after
anchor: "[server]\n"
new: "port = 8080\n"
Run it:
go run ./cmd/agentedit -- -spec edits.yaml -dry-run -format text
tools
Use the local `company` CLI for German Handelsregister, OffeneRegister, and OpenCorporates company lookup with structured output. Prefer it when an agent needs registry-backed company research before lead scoring, outreach, or CRM/database updates.
tools
Send or validate SMTP mail flows with the `agentsmtp` CLI. Use when an agent needs a small SMTP submission tool with provider presets for Gmail or Google Workspace, structured output, and configurable auth through password or app-password.
tools
Use the local `agentrunpod` CLI to submit, inspect, and cancel RunPod serverless jobs with structured output. Prefer it when an agent needs an env-configurable wrapper around the RunPod HTTP API instead of ad hoc curl commands.
tools
Execute shell commands with the local `agentrun` CLI. Use when an agent needs timeout control, bounded stdout and stderr capture, or structured command results instead of direct raw process execution.