bradygaster/squad is a tool that creates a human-directed team of AI development agents inside a project repository through GitHub Copilot. Developers use it to delegate work among persistent specialists such as frontend, backend, testing, and lead agents while retaining responsibility for decisions and review. The catalogue entries are the skills, agents, and instructions that define and coordinate those team members.
Borrowing it
Nothing to install: this file belongs to bradygaster/squad. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bradygaster/squad/dev/.github/skills/gh-aw-reliability/SKILL.mdgit clone --depth 1 https://github.com/bradygaster/squadWrote 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.
[](https://agentmods.dev/skills/bradygaster/squad/gh-aw-reliability)<a href="https://agentmods.dev/skills/bradygaster/squad/gh-aw-reliability"><img src="https://agentmods.dev/badge/skills/bradygaster/squad/gh-aw-reliability/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bradygaster/squad/gh-aw-reliability"><img src="https://agentmods.dev/badge/skills/bradygaster/squad/gh-aw-reliability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00019 | $0.00352 |
| Opus 5.5 | $0.00008 | $0.00141 |
| Sonnet 5.5 | $0.00004 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
gh-aw-reliability 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 1mo 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.
What it actually says
Context
Use this skill when creating or changing Squad GitHub Agentic Workflow sources, safe outputs, authorization, or prompt inputs. Prompt prose can look correct while the compiled workflow does nothing or authorizes the wrong action.
Patterns
- Treat workflow source, compiled lock output, and declared safe outputs as a single contract.
- Strict-compile the workflow and inspect the emitted artifact; a zero exit code alone is not enough when a specific handler, input, or protected-file rule is required.
- Enumerate all call sites when changing parsing, normalization, ownership binding, or command routing.
- Bind authorization, labels, and mutable actions to committed provenance rather than an unverified working-tree claim.
- Fail closed when the compiler, required tool, or evidence needed to prove the contract is unavailable.
- Test a realistic mutation of the live source and prove the relevant gate fails.
Examples
test/gh-aw-deps-worker-workflow.test.ts mutates a real worker source, runs the compiler, then
asserts on the compiled protected-files contract. test/gh-aw-activate-roster-binding.test.ts
checks roster-derived authorization behavior.
Anti-Patterns
- Validating only prompt text or a hand-built configuration object
- Letting unavailable workflow tooling silently skip a protection gate
- Testing one parser helper while leaving an alternate command-dispatch caller untested
- Minting labels or authorization from role prose instead of committed roster evidence
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.
- 1mo ago First seen · 40 lines · 19 tokens per session scan A f16bfe9386d4
gh-aw-reliability is a skill published in the GitHub repository bradygaster/squad (3,295 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 352 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-12.
Other skills, from other repositories
Test Quality Inspector
Systematically inspect unit and E2E tests to verify they test the right behavior, provide meaningful coverage, and catch real regressions.
webapp-testing
Automated webapp testing with Playwright. Server management, UI testing, visual debugging, and reconnaissance-first approach.
kane-cli
End-to-end (E2E) test generation and execution with KaneCLI. Generate tests from a PRD, specification, or user-provided description via the assurance commands (use-cases, acceptance criteria, scenarios, runnable test.md tests; never write test cases by hand). Execute them on desktop web (Chrome, the default), Android…
Condition-Based Waiting
Replace arbitrary timeouts with condition polling for reliable async tests.
playwright
You are writing end-to-end tests with Playwright. Apply these conventions.
webapp-testing
Web application testing principles. E2E, Playwright, deep audit strategies.