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 gpsaggese/helpers --skill testing.update_test_outcomesgit clone --depth 1 https://github.com/gpsaggese/helpersWrote 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/gpsaggese/helpers/testing.update_test_outcomes)<a href="https://agentmods.dev/skills/gpsaggese/helpers/testing.update_test_outcomes"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/testing.update_test_outcomes/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/gpsaggese/helpers/testing.update_test_outcomes"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/testing.update_test_outcomes.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 | $0.00008 | $0.00688 |
| Opus 5.5 | $0.00003 | $0.00275 |
| Sonnet 5.5 | $0.00002 | $0.00138 |
| Haiku 4.5 | $0.00001 | $0.00069 |
Grade A, and why
testing.update_test_outcomes 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 yesterday.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
- The user passes a list of tests, or a repro script, with failing tests
<FAILING_TESTS>whose actual and expected outputs mismatch
Important
- For all code, follow
.claude/skills/coding.rules.md - Follow the invariants and conventions for unit tests in
.claude/skills/testing.rules.md
Workflow
Run the Failing Tests
- Run the tests one at a time, the way the user suggested, to confirm they fail due to mismatching outputs
Classify the Assertion Method
-
For each failing test method, check whether the result is checked with
self.check_string()self.assert_equal()or a similar assertion (e.g.,hunteuti.assert_sys_calls(),self.assertEqual())
-
Print a table with the following info: path of test | fail / pass | check_string or assert_equal
| Path | Test | Status | Assertion Method | |------|------|--------|------------------| | dev_scripts_helpers/documentation/test/test_notes_to_pdf.py | Test_notes_to_pdf_latex_options::test1 | FAIL | self.assert_equal() with fuzzy_match=True | | dev_scripts_helpers/documentation/test/test_notes_to_pdf.py | Test_notes_to_pdf_latex_options::test2 | FAIL | self.assert_equal() with fuzzy_match=True | | dev_scripts_helpers/documentation/test/test_notes_to_pdf.py | Test_notes_to_pdf_output_types::test1 | FAIL | self.assert_equal() with fuzzy_match=True | -
Save this to
tmp.update_test_outcomes.failing_tests.md
Update the Expected Output
- For each failing test method:
- If the result is checked with
self.check_string()- Run the test with the pytest option
--update_goldento refresh the output
- Run the test with the pytest option
- If the result is checked with
self.assert_equal()or a similar assertion (e.g.,hunteuti.assert_sys_calls()), read the file<TEST_DIR>/tmp.initial.actual.txt(e.g.,dev_scripts_helpers/documentation/test/outcomes/Test_run_pandoc_to_html.test1) that holds the actual variable, and update theexpectedvariable- E.g.,
expected = """ [{'args': (f'jupytext --to ipynb --update {py_file}',), 'function': 'hsystem.system', 'kwargs': {}}, {'args': (f'jupytext --sync {py_file}',), 'function': 'hsystem.system', 'kwargs': {}}] """
- E.g.,
- If the result is checked with
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.
- yesterday First seen · 71 lines · 8 tokens per session scan A b6f05d2c8547
testing.update_test_outcomes is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 8 tokens to every session and 688 once invoked, about $0.0000 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 2026-11-06.
testing.update_test_outcomes compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| testing.update_test_outcomesgpsaggese/helpers | Skill | 158 | today | Apache-2.0 | A | 8 | Claude Code |
| test-masterJeffallan/claude-skills | Skill | 12k | 8d ago | MIT | A | 104 | Claude Code |
| migrate-xunit-to-xunit-v3dotnet/skills | Skill | 5.8k | today | MIT | A | 149 | Claude Code |
| go-testingGentleman-Programming/gentle-ai | Skill | 8.5k | today | MIT | A | 26 | Claude Code, Codex |
| principle-test-behavior-not-implementationmichael-denyer/pstack-claude | Skill | 4.1k | yesterday | MIT | A | 50 | Claude Code |
| dart-testdartsim/dart | Skill | 1.2k | today | BSD-2-Clause | A | 18 | Claude Code, Codex |
| test-generatorrshankras/claude-code-apple-skills | Skill | 867 | today | MIT | A | 33 | Claude Code |