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/codagent-ai/agent-skills/test-flowsnpx skills add Codagent-AI/agent-skills --skill test-flowsgit clone --depth 1 https://github.com/Codagent-AI/agent-skillsWhat 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 | $0.00066 | $0.00714 |
| Opus 5 | $0.00033 | $0.00357 |
| Sonnet 5 | $0.00013 | $0.00143 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
test-flows 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Flows
Exercise the checked-out product as a user or real client would. This is a lightweight flow check, not automated validation or formal acceptance preparation.
Inputs
Read the caller-supplied:
- approved behavior or planning artifacts;
- concise implementation summary;
- verification scope: representative full pass or named targeted flows;
- evidence directory when the selected scope includes UI flows or durable evidence is requested.
If expected behavior is unavailable, report what is missing instead of inferring the contract from implementation alone. If a selected UI flow has no evidence directory, report the missing input instead of testing that flow without its required screenshot.
Select flows
For a representative full pass, identify the meaningful changed journeys and public surfaces that
collectively demonstrate the delivered behavior. When an approved test plan exists, exercise its
required and activated conditional AT-* flows. Otherwise keep the inventory proportional to the
small change rather than replaying every requirement scenario or input variation.
For targeted verification, exercise the named affected flows and obvious direct dependencies. Verify the prior finding first. Do not start a new broad review or search unrelated surfaces for additional issues.
Use typical data, configuration, and roles. Do not fuzz, try bizarre inputs, or build an exhaustive edge-case matrix. Test an error or boundary state only when it belongs to a normal selected flow.
Exercise the public surface
Use the project's normal setup, build, install, seed, and start commands needed to expose the current worktree. Do not run automated unit, integration, or end-to-end suites, linters, Validator, or CI.
- Operate web, mobile, desktop, and terminal UIs through their real interface.
- Call APIs through their documented HTTP, SDK, or CLI surface as a client would.
- Invoke CLIs and libraries through their public commands or APIs.
- Trigger background behavior through its normal entry point and inspect the observable result.
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.
- 3d ago First seen · 73 lines · 66 tokens per session scan A ae6d2f897d38
test-flows is a skill published in the GitHub repository Codagent-AI/agent-skills (30 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 714 once invoked, about $0.0003 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 skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
test-conversion
Workflow for converting unit tests to browser tests for Project Bedrock. Invoke this when the user wants to remove complex Browser dependencies from tests.
agui-dotnet-cross-language-tests
Author cross-language interop tests that verify the AG-UI .NET SDK is wire-compatible with the TypeScript SDK — a Vitest TS client driving a C# CrossLanguage.TestServer over HTTP, both directions, including protobuf byte-parity against @ag-ui/proto. USE FOR: adding or modifying cross-language interop coverage…
cli-e2e-testcase-writer
Use when adding or updating Go CLI E2E coverage for one tests/clie2e/{domain} domain of the compiled lark-cli, especially when the work requires live --help or schema exploration, scenario-based clie2e.RunCmd workflows, and per-domain coverage.md maintenance.
harness-test-writer
Add regression test cases to the Bifrost provider harness (the Postman collection run via make run-provider-harness-test) based on a merged PR or a GitHub issue. Fetches the PR/issue, traces the affected wire path in the codebase, checks existing harness coverage, designs cases following harness conventions, inserts…
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.