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 makifbaysal/tasktrooper --skill boundary-negative-testinggit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/boundary-negative-testing)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/boundary-negative-testing"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/boundary-negative-testing/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/makifbaysal/tasktrooper/boundary-negative-testing"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/boundary-negative-testing.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 | $0.00036 | $0.00421 |
| Opus 5.5 | $0.00014 | $0.00168 |
| Sonnet 5.5 | $0.00007 | $0.00084 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
boundary-negative-testing 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 8d 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.
What it actually says
Boundary and Negative Testing
Data catalogue
- Strings: empty, whitespace-only, 1 char, max, max+1, 10x max, leading/trailing spaces, emoji/ZWJ, RTL text, combining marks,
<b>x</b>and<img src=x onerror=alert(1)>(must render as inert text, never execute),' OR 1=1 --(as literal data),../../etc/passwdin a filename-ish field. - Numbers: −1, 0, 1, max, max+1, a decimal where an integer is expected,
1e309,NaN. - Dates: leap day, a DST transition, a timezone boundary, past/future limits the domain implies.
- Files: 0 bytes, just over the size limit, wrong MIME type with a correct-looking extension.
- Collections: 0 items, 1 item, exactly the page size, page size + 1.
- Concurrency: double submit, two sessions editing the same record.
- Dependency down: the stubbed dependency returns 5xx/timeout (test-data-and-stubs), or
route "**/api/<dep>/**" --status=500for a UI-only case.
Flow-level cases
Unauthorized access, missing resources (404 paths), concurrent/duplicate submission, partial failure of a dependency.
Recording
Record every boundary you probed as its own test case on the task, passing ones included — absence of evidence is not evidence of absence, and a boundary nobody can see you tried is one the next reader has to try again. A boundary that cannot exist here (the field is an enum, the endpoint is internal-only) is a case too: record it invalid with that reason.
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.
- 8d ago First seen · 25 lines · 36 tokens per session scan A cff9a5a092f4
boundary-negative-testing is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 421 once invoked, about $0.0001 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 2026-10-05.
Other skills, from other repositories
qa-acceptance
Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.
nemo-automodel-model-onboarding
Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.
amc-run-sample-calibration
Run end-to-end calibration on the shipped sample dataset (sdg082sampledata010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.
nemo-automodel-recipe-development
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
mcore-testing
Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.
i4h-catheter-navigation-e2e
End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.