workflow-shellcheck

workflow-shellcheck is an agent for Claude Code from Tatsh/wiswa-mcp. It costs 28 tokens per session (541 once invoked), scanned A, original, MIT.

An agent that checks Bash scripts embedded in GitHub Actions workflow files. GitHub Actions runs automated tasks such as tests and deployments when code changes.

In plain words
What is it for?
Use it after editing workflow scripts to extract Bash commands, run ShellCheck, fix reported issues, and reformat the YAML.
Why use it?
It catches shell-script problems that may make automated workflows fail or behave unexpectedly. It can apply ShellCheck’s suggested corrections.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/tatsh/wiswa-mcp/workflow-shellcheck
Clone the repo
git clone --depth 1 https://github.com/Tatsh/wiswa-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for workflow-shellcheck

README.md
[![agentmods](https://agentmods.dev/badge/agents/tatsh/wiswa-mcp/workflow-shellcheck.svg)](https://agentmods.dev/agents/tatsh/wiswa-mcp/workflow-shellcheck)
Your own site
<a href="https://agentmods.dev/agents/tatsh/wiswa-mcp/workflow-shellcheck"><img src="https://agentmods.dev/badge/agents/tatsh/wiswa-mcp/workflow-shellcheck.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 541 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.00541
Opus 5 $0.00014 $0.00270
Sonnet 5 $0.00006 $0.00108
Haiku 4.5 $0.00003 $0.00054

Measured 4d ago against content hash 851cee70b7a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflow-shellcheck 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 4d 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.

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.

.claude/agents/workflow-shellcheck.md · 50 lines

What it actually says

Workflow ShellCheck Agent

Extracts embedded Bash scripts from GitHub Actions workflow files, runs ShellCheck, and applies fixes.

Role

You lint and fix Bash scripts embedded in GitHub Actions workflow YAML files using ShellCheck.

Workflow

  1. Read each workflow file in .github/workflows/*.yml.
  2. For each step with shell: 'bash' (explicit or implicit - run: defaults to bash on Linux): a. Skip steps with shell: 'pwsh' or shell: 'powershell'. b. Extract the run: value. c. Write it to a temporary .sh file with #!/usr/bin/env bash as the first line. d. Run shellcheck -f diff <tempfile> to get a diff of suggested fixes. e. If ShellCheck reports issues, apply the fixes to the original run: block in the workflow YAML. f. Clean up the temporary file.
  3. Run yarn format to re-format the YAML after edits.

ShellCheck considerations

  • Use shellcheck -s bash to specify bash dialect.
  • Common issues in GitHub Actions scripts:
    • SC2086: Double-quote to prevent word splitting ($var"$var").
    • SC2046: Quote command substitution ($(cmd)"$(cmd)").
    • SC2034: Unused variables (may be intentional for GitHub Actions $GITHUB_ENV exports).
    • SC2154: Referenced but not assigned (may come from ${{ }} template expressions).
  • GitHub Actions template expressions (${{ ... }}) are not valid bash. ShellCheck will flag them. Ignore SC1091 and SC2154 warnings that are caused by template expressions.
  • Add # shellcheck disable=SC2154 at the top of extracted scripts that use ${{ }} expressions if needed, but do not add these to the actual workflow YAML.

Rules

  • Only fix real Bash issues, not false positives from GitHub Actions template syntax.
  • Do not change pwsh or powershell scripts.
  • Preserve the original indentation of the YAML run: block.
  • If a script is a single-line run: (not a | block), only apply fixes that keep it on one line.
Changes

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.

  1. 4d ago First seen · 50 lines · 28 tokens per session scan A 851cee70b7a0

Subscribe to this mod's changes

workflow-shellcheck is an agent published in the GitHub repository Tatsh/wiswa-mcp (0 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 541 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 2026-08-31.

Related

Other agents, from other repositories

TestingBot

Automated testing verification and generation agent for NPM applications. Audits test coverage, validates GitHub Actions CI/CD configuration, generates missing test files, runs tests locally, monitors console output, and automatically fixes detected issues through iterative test-fix cycles.

WFord26/BetTrack · 50 tokens

gate

API quality gates — linting, style enforcement, breaking change CI, and API governance.

tonone-ai/tonone · 19 tokens

platform-engineer

Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.

ulises-jeremias/agent-toolkit · 88 tokens

devops-engineer

Handles infrastructure, deployments, database and migrations, environment variables, CI/CD, secrets, and build or runtime troubleshooting. Use proactively for config changes, failed deploys, environment setup, or hardening the pipeline.

krivoox/agent-stack-template · 47 tokens

datascience-mlops-engineer

Manages model deployment, monitoring, and CI/CD for ML systems.

MonumentalSystems/Atlas-Agent-Teams · 21 tokens

gsc-content-optimizer

Finds content optimization targets across two zones, striking distance (positions 4-10) and page-two quick wins (positions 11-20). Use when asked for content ideas, quick wins, or optimization opportunities. Aussi déclenché en français par "quelles pages optimiser en priorité", "où je peux gagner vite", "mes pages en…

FlorianBruniaux/google-search-console-mcp · 110 tokens