Borrowing it
Nothing to install: this file belongs to terrene-foundation/metis. 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/terrene-foundation/metis/main/.claude/skills/test-skip-discipline/SKILL.mdgit clone --depth 1 https://github.com/terrene-foundation/metisWrote 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/terrene-foundation/metis/test-skip-discipline)<a href="https://agentmods.dev/skills/terrene-foundation/metis/test-skip-discipline"><img src="https://agentmods.dev/badge/skills/terrene-foundation/metis/test-skip-discipline/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/terrene-foundation/metis/test-skip-discipline"><img src="https://agentmods.dev/badge/skills/terrene-foundation/metis/test-skip-discipline.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 | $0.00043 | $0.02927 |
| Opus 5 | $0.00022 | $0.01463 |
| Sonnet 5 | $0.00009 | $0.00585 |
| Haiku 4.5 | $0.00004 | $0.00293 |
Grade A, and why
test-skip-discipline 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 7d 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.
This is a copy
95% identical to test-skip-discipline — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-Skip Discipline
The distinguishing rule: skip if the test cannot execute (missing credentials, wrong platform, feature flag off); fail if the test executes but the system is broken.
Every test.skip(...) / pytest.skip(...) / #[ignore] is one of two things. One is a legitimate "we cannot run this test here" gate. The other is a silent mask over a broken system — the test ran, the upstream was degraded, the skip absorbed the signal, and the runner reports green for an unknown period. The second class is BLOCKED.
The Problem (Grounded In The STP Incident)
Downstream STP's Playwright spec tests/e2e/stp-chatbot-scope.spec.ts contained test.skip(chatStatus >= 500, ...) which was the only reason the spec wasn't red despite POST /api/chat returning 503 on every run. The skip masked the Bedrock gap for an unknown period; nobody noticed until a human filed issue #52.
This is not Bedrock-specific. Any test that skips on the system-under-test's runtime behaviour silently absorbs every non-functional AI path — OpenAI auth failures, Anthropic rate-limits, Google SSL handshakes, local Ollama not running, any upstream degradation. In a multi-downstream template ecosystem, every USE repo that copies the pattern inherits the masking.
Origin: workspaces/use-feedback-triage/journal/0003-GAP-test-skip-masks-ai-failures.md.
Acceptable Skip Patterns
Skip gates that check whether the test can execute at all — before the system-under-test is invoked. The check is on the environment, not on the response.
1. credential_absent — Tier 2 Integration Tests Requiring Real Cloud Credentials
// DO — skip when the credential isn't present; the test cannot execute without it
test("bedrock claude returns a completion", async ({ page }) => {
test.skip(
!process.env.AWS_BEARER_TOKEN_BEDROCK,
"requires AWS_BEARER_TOKEN_BEDROCK",
);
// ... real upstream call; 5xx here is a FAILURE, not a skip
});
# DO — pytest credential gate
@pytest.mark.skipif(
not os.getenv("AWS_BEARER_TOKEN_BEDROCK"),
reason="requires AWS_BEARER_TOKEN_BEDROCK for live Bedrock call",
)
def test_bedrock_claude_completion():
...
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.
- 7d ago First seen · 237 lines · 43 tokens per session scan A 3fb8701afbd3
test-skip-discipline is a skill published in the GitHub repository terrene-foundation/metis (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 2,927 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to test-skip-discipline, differing in 5 lines, and is treated as a copy.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.