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 backend-manual-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/backend-manual-testing)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/backend-manual-testing"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/backend-manual-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/backend-manual-testing"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/backend-manual-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 | $0.00044 | $0.00866 |
| Opus 5.5 | $0.00018 | $0.00346 |
| Sonnet 5.5 | $0.00009 | $0.00173 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
backend-manual-testing 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Drive the real surface**: `curl`/httpie against the running API (api-contract-testing). Record the exact request and the exact response — status, body, headers that matter. How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Manual Testing
Overview
Manual verification of a backend task means booting the real service (and its worker, if the repo has one) from the task branch and executing your scenario plan against it. The scenario plan comes first and comes from the task description and acceptance criteria alone (scenario-plan-first) — you never derive cases from the diff or the source.
Preconditions: case matrix recorded with record_test_cases (scenario-plan-first); environment chosen per test-environment-selection (local by default — side effects are only observable there — else the repository's stage deploy target; never prod).
Booting in the workspace
- Learn how the project runs — in this order:
search_memory(scope=project) for a boot recipe from an earlier round,get_project_brieffor the components/commands/ports, the repository'sbuild_command/test_command/verify_commandsettings, README / Makefile / docker-compose / example env files, and any comment the developer left (a clean run leaves none).list_linksshows what this component talks to — the side effects you'll need to verify and the dependencies to stub. Do not guess ports, flags, or env vars when the project declares them. - Provision dependencies. Database and other infrastructure run as disposable containers when a container runtime (podman/docker) is available; run the project's real migrations and a minimal seed. External third-party services are stubbed so failure scenarios are drivable (test-data-and-stubs).
- Start the processes: the API server, and every worker/consumer process the repo defines (see worker-job-testing). Keep their logs streaming to a per-task scratch file:
QA=${TMPDIR:-/tmp}/tt-<task-key>/qa; mkdir -p "$QA"; ... > "$QA/api.log" 2>&1 &. - Smoke check before scenarios: health endpoint answers, migrations applied, worker connected. A failed boot is itself a finding — capture the exact error output.
Executing scenarios
For each scenario in the plan, in order:
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 · 43 lines · 44 tokens per session scan A 0f901d574a0d
backend-manual-testing is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 866 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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.
jetson-video-pipeline
Use when planning, executing, and independently validating Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or concise acceptance workflows.
proof-e2e
Build E2E test specs for critical user journeys — Playwright or Cypress, page objects, setup/teardown, CI config. Use when asked to "write E2E tests", "end-to-end testing", "browser tests", "UI tests", or "Playwright tests".
proof-strategy
Produce a test strategy for a project or feature — risk map, test type decisions, coverage targets, CI config. Use when asked to "create test strategy", "what should we test", "testing plan", or "improve test coverage".
proof-api
Build API test suites — endpoint testing, contract testing, load testing for REST/GraphQL/gRPC APIs. Use when asked to "test this API", "API tests", "endpoint testing", "contract tests", or "load test".
proof-recon
Testing reconnaissance — inventory all tests, frameworks, coverage, CI integration, and assess testing maturity for project takeover. Use when asked to "understand the tests", "testing assessment", "what's tested", or "test inventory".