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/kolodkin/devpowers/action-runnpx skills add kolodkin/devpowers --skill action-rungit clone --depth 1 https://github.com/kolodkin/devpowersWhat 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 | $0.00074 | $0.02195 |
| Opus 5 | $0.00037 | $0.01097 |
| Sonnet 5 | $0.00015 | $0.00439 |
| Haiku 4.5 | $0.00007 | $0.00219 |
Grade A, and why
action-run scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
s=$(curl -fsSL \ How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Action Run Skill
Trigger any GitHub Actions workflow_dispatch workflow by name, gather required inputs, monitor it to completion, and fix failures automatically — driven through the GitHub MCP server's actions toolset (mcp__plugin_devpowers_github__actions_*, mcp__plugin_devpowers_github__get_job_logs), exactly the way /check-pr drives PR/CI status through mcp__plugin_devpowers_github__pull_request_read. No gh CLI.
Invocation Format
/action-run <workflow description> [key=value] [flag] ... [branch=<name>]
Examples:
/action-run hello
/action-run hello name=Mark shout
/action-run pypi publish tag=v0.0.8 pre-release
/action-run pypi publish tag=v0.0.8 branch=main
/action-run generate migration message="add users table"
Step 0 — Ensure the GitHub MCP actions toolset is available
This skill drives everything through the actions toolset of the github MCP server bundled with this plugin — its .mcp.json loads as mcp__plugin_devpowers_github__*, and the X-MCP-Toolsets: all header turns the actions tools on.
- If
mcp__plugin_devpowers_github__get_job_logs(and themcp__plugin_devpowers_github__actions_*tools) are visible in your tool list, proceed. - If they're missing, the plugin's bundled
githubMCP didn't connect — almost always becauseGH_TOKENisn't set (it authenticates withBearer ${GH_TOKEN}). Tell the user toexport GH_TOKEN=<pat>(a long-lived PAT) and restart Claude Code (or run/reload-plugins), then re-invoke/action-run. Stop until the server loads.
Triggering workflow_dispatch needs a token with Actions: write (classic workflow scope / fine-grained Actions: write). A read-only token can list and inspect runs, but run_workflow will fail with 403.
Tool shape: the hosted server groups Actions operations into method-based tools — mcp__plugin_devpowers_github__actions_run_trigger (methods run_workflow, rerun_failed_jobs, rerun_workflow_run, cancel_workflow_run), mcp__plugin_devpowers_github__actions_list (list_workflows, list_workflow_runs, list_workflow_jobs), mcp__plugin_devpowers_github__actions_get (get_workflow_run), and the standalone mcp__plugin_devpowers_github__get_job_logs. Server versions may rename these or shift methods; map the intent below to whatever mcp__plugin_devpowers_github__* actions tools your session actually exposes, and read each tool's registered schema for exact filter/pagination parameters.
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.
- 2d ago First seen · 134 lines · 74 tokens per session scan A cd183ed64b72
action-run is a skill published in the GitHub repository kolodkin/devpowers (2 stars, last pushed 23d ago), licensed MIT. It adds 74 tokens to every session and 2,195 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.