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 skills add projectbluefin/testsuite --skill behavegit clone --depth 1 https://github.com/projectbluefin/testsuiteWrote 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/projectbluefin/testsuite/behave)<a href="https://agentmods.dev/skills/projectbluefin/testsuite/behave"><img src="https://agentmods.dev/badge/skills/projectbluefin/testsuite/behave/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/projectbluefin/testsuite/behave"><img src="https://agentmods.dev/badge/skills/projectbluefin/testsuite/behave.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 | $0.00027 | $0.05727 |
| Opus 5.5 | $0.00011 | $0.02291 |
| Sonnet 5.5 | $0.00005 | $0.01145 |
| Haiku 4.5 | $0.00003 | $0.00573 |
Grade A, and why
behave 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 22d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
actual = subprocess.run(["xdg-mime", "query", "default", "application/pdf"], The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/ambiguous-steps.md 1.7 KB
- references/cached-image-gate.md 4.8 KB
- references/flatpak-permissions.md 2.7 KB
- references/mocking-interactive-cli.md 2.4 KB
- references/shared-ssh.md 6.3 KB
- references/smoke-vs-ssh.md 1.1 KB
- references/ujust-noninteractive.md 3.2 KB
- references/unit-test-module-stubs.md 7.1 KB
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.
- 22d ago Changed · +3 lines fd3939b67a0c
- 1mo ago Changed · -1 lines f3ebcbf58f6f
- 1mo ago First seen · 499 lines · 27 tokens per session scan A b90ac42b405a
behave is a skill published in the GitHub repository projectbluefin/testsuite (3 stars, last pushed today), with no licence file. It adds 27 tokens to every session and 5,727 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
Behave BDD Testing
Python BDD testing with Behave framework using Gherkin feature files, step definitions, environment hooks, and Selenium integration for behavior-driven acceptance testing.
parallelism
Run Ginkgo suites in parallel — ginkgo -p / --procs, the separate-process (not goroutine) model, SynchronizedBeforeSuite/SynchronizedAfterSuite vs BeforeSuite, GinkgoParallelProcess() for sharding ports/tmpdirs/databases, building a binary once via gexec, piping child-process output to GinkgoWriter, and what N…
tables-and-dynamic-specs
Parameterize and generate Ginkgo specs — DescribeTable/Entry table-driven specs, Entry descriptions (string, nil, closure, EntryDescription), PEntry/FEntry and per-Entry decorators, DescribeTableSubtree, generating specs in a construction-time loop, loading fixtures in TestXxx before RunSpecs, and shared-behavior…
writing-specs
Author good Ginkgo specs — container nodes (Describe/Context/When), subject nodes (It/Specify), setup/cleanup nodes (BeforeEach, JustBeforeEach, AfterEach, DeferCleanup, BeforeSuite/AfterSuite), the "declare in container, initialize in BeforeEach" rule, separating creation from configuration, reusable test helpers…
ci
Configure Ginkgo for continuous integration — the recommended CLI flag set and the rationale for each flag (-r -p --randomize-all --randomize-suites --fail-on-pending --fail-on-empty --keep-going --cover --race --trace --json-report --timeout --poll-progress-after/-interval), invoking via go run to pin the CLI to…
debugging-failures
Diagnose a failing Ginkgo suite as an agent — always run with --json-report into a predictable temp/gitignored location, read the terminal verdict line, then use jq to extract structured failure details (name, message, file:line, panic value, captured logs). Covers the panicked-vs-failed trap, panic locations pointing…