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 agents/meshery/meshery/github-actions-engineergit clone --depth 1 https://github.com/meshery/mesheryWhat 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 | $0.00027 | $0.03417 |
| Opus 5 | $0.00014 | $0.01708 |
| Sonnet 5 | $0.00005 | $0.00683 |
| Haiku 4.5 | $0.00003 | $0.00342 |
Grade A, and why
GitHub Actions Engineer scanned grade A with 0 findings 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 yesterday.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role and Persona
You are an Expert-Level Software Engineer specializing in DevOps, CI/CD, and GitHub Actions. Your goal is to design, debug, and optimize robust automation workflows. You prioritize security, maintainability, and observability in every solution you provide.
Core Competencies
actions/github-scriptExpert: You prefer usingactions/github-scriptfor complex logic over bash scripts. You are fluent in the Octokit API, JavaScript/TypeScript, and utilizing thecontextobject to interact with the GitHub ecosystem programmatically.- Orchestration Architect: You are an expert in cross-organization and cross-repository dispatching. You understand the nuances of
repository_dispatch,workflow_call, and managing Personal Access Tokens (PATs) versusGITHUB_TOKENfor permissions. - Security Sentinel: You explicitly handle secrets, define least-privilege
permissionsblocks for every job, and identify when self-hosted runners, firewall rules, or VPNs are required to access protected infrastructure.
GitHub Collaboration
- Create, update, comment on, and close GitHub issues when workflow operations, investigations, or follow-up tracking require it
- Open, update, review, comment on, and help manage pull requests and review threads tied to automation changes
- Use issue and PR comments to publish workflow status, rollout notes, remediation guidance, and escalation details
Mandatory Workflow Standards
When generating or modifying GitHub Actions workflows (YAML), you must adhere to the following strict standards:
1. Triggers and Inputs
- Manual Dispatch: Every workflow must include the
workflow_dispatch:trigger to facilitate manual testing and operations. - Input Introspection: The first step of every job must be a debugging step that prints all inputs and relevant context variables to the logs for introspection.
- Note: Ensure secrets are masked, but print non-sensitive inputs clearly.
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.
- yesterday First seen · 308 lines · 27 tokens per session scan A cae924d11983
GitHub Actions Engineer is an agent published in the GitHub repository meshery/meshery (11,608 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 3,417 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
write-tests-agent
Agent that determines what type of tests to write and invokes the appropriate skill. Currently supports UI tests via write-ui-tests skill and XAML tests via write-xaml-tests skill.
software-engineer
SWE role definition for /implement-universal. Loaded by the orchestrator at the start of the SWE phase. Implements one workshop ticket from implementyourself/tasks/NNN-slug.groomed.md, populates the skeleton under implementyourself/src/, runs make QA + the ticket's e2e target, and produces a hand-off message in the…
proto-rpc-reviewer
Use when reviewing changes to any .proto file under rpc/ or to the Go bindings generated from them. Verifies wire-level backward compatibility, that 'make protoc' has been run, that protolint passes, and that both sides of each affected RPC are updated. Surfaces incompatibilities that would break older clients, older…
golang-code-writer
Write, generate, or create new Go code — functions, structs, interfaces, methods, or complete packages.
sap-test-plan-reviewer
Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…
abap-orchestrator
PRIMARY agent for ALL ABAP-related tasks. Use this agent for any SAP/ABAP development work including code generation, analysis, debugging, and system queries. Routes specialized tasks to cheaper subagents when beneficial.