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 ddddjaak/se-skills --skill test-report-reviewgit clone --depth 1 https://github.com/ddddjaak/se-skillsWrote 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/ddddjaak/se-skills/test-report-review)<a href="https://agentmods.dev/skills/ddddjaak/se-skills/test-report-review"><img src="https://agentmods.dev/badge/skills/ddddjaak/se-skills/test-report-review/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/ddddjaak/se-skills/test-report-review"><img src="https://agentmods.dev/badge/skills/ddddjaak/se-skills/test-report-review.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 | $0.00112 | $0.04215 |
| Opus 5 | $0.00056 | $0.02107 |
| Sonnet 5 | $0.00022 | $0.00843 |
| Haiku 4.5 | $0.00011 | $0.00421 |
Grade A, and why
test-report-review 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 11d 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Report Review
Overview
A test report that says "all tests passed" is not the same as a test report that proves it. A reviewer reading a test report sees test items with checkmarks. A reviewer reading a test report against the test plan sees gaps: pass/fail criteria that were silently relaxed, test items marked "passed" with data that contradicts the threshold, missing test environment details that make results unreproducible, and orphaned test results that test nothing in the requirements.
This skill reviews a test report document against its governing test plan and the relevant review checklist. It does not trust the report's conclusions — it verifies them against the criteria the test plan defined. Every finding cites a specific checklist item ID and, where applicable, the test plan criterion the report data is inconsistent with.
When to Use
- A test report has been submitted for review, sign-off, or milestone gate
- Preparing for a formal review meeting where the test report is the primary evidence
- The test report's conclusions ("all passed") appear inconsistent with known issues or defect counts
- A downstream team has raised questions about whether testing was adequate
- Validating that regression testing or a re-spin touched all affected areas
- After a requirements or architecture change — to confirm tests were updated to match
When NOT to use:
- The test report is a draft the test team has not self-reviewed yet (ask them to self-review first)
- Reviewing the test plan itself (use
design-reviewwith the Test lens instead) - Typos and formatting issues in the test report (these do not need a full checklist-driven review)
- The test report has no associated test plan (nothing to compare against — the review cannot be meaningful)
- Pure traceability audit without correctness verification (use
traceability-matrixfor coverage-only checks)
Context Boundary
This skill reads exactly three categories of input:
- Test report — the document under review, at the path provided by the user
- Test plan — the governing test plan that defines pass/fail criteria, test environment, and traceability expectations
- Relevant checklist(s) — loaded based on report type (Step 1), from
references/
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.
- 11d ago First seen · 282 lines · 112 tokens per session scan A 345322a2f2d2
test-report-review is a skill published in the GitHub repository ddddjaak/se-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 4,215 once invoked, about $0.0006 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 2026-08-31.
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.