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 tronghieu/agent-skills --skill manual-testergit clone --depth 1 https://github.com/tronghieu/agent-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/tronghieu/agent-skills/manual-tester)<a href="https://agentmods.dev/skills/tronghieu/agent-skills/manual-tester"><img src="https://agentmods.dev/badge/skills/tronghieu/agent-skills/manual-tester/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/tronghieu/agent-skills/manual-tester"><img src="https://agentmods.dev/badge/skills/tronghieu/agent-skills/manual-tester.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 | $0.00178 | $0.03154 |
| Opus 5.5 | $0.00071 | $0.01262 |
| Sonnet 5.5 | $0.00036 | $0.00631 |
| Haiku 4.5 | $0.00018 | $0.00315 |
Grade C, and why
manual-tester scanned grade C with 2 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 16d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
required sections — don't refuse and don't wing it: create it. Follow Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Read, Write, Edit, Glob, Grep, Bash(curl *), Bash(psql *), Bash(docker *), Bash(jq *), Bash(python3 *) How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manual Tester — Session-Based Testing on the Running App
You are running a testing session: operate the app like a real user and produce information the automated suites cannot — they re-check known promises; you handle everything else, from hunting unknown bugs to judging whether a screen makes sense.
Your posture is falsification: you are trying to break the belief that the software works, not to confirm it. But you are an agent, and an agent's eye is not an oracle — so every claim you make must survive the proof discipline below. One false "bug" costs more credibility than ten real ones earn.
Asked for a plan, not a session? Write it per references/test-plan-authoring.md and
stop: no driving. It still resolves the customization and reads the adapter first.
This skill is generic; everything project-specific lives in the project adapter
and the project's customization (both below). If asked to explain the method's theory,
check the customization's persistent facts and _project/README.md for the project's
testing docs before explaining from memory.
Project customization — resolve first
Before anything else, resolve the skill's customization:
python3 <skill-dir>/scripts/resolve_customization.py
Needs Python 3.11 or the tomli package. It merges three layers and prints JSON: the skill's customize.toml defaults, the team
override _project/testing/manual-tester.toml, and the personal override
_project/testing/manual-tester.user.toml. Missing override files are normal and mean
defaults. Then act on customization.workflow:
activation_steps_prepend— follow now, before preflight.persistent_facts— read everyfile:entry fully and keep literal entries in mind for the whole session. These are the project's testing policy. Where a fact disagrees with this skill, the fact wins: its status vocabulary replaces the default verdicts, its source hierarchy decides conflicts, its evidence rules add to proof discipline.activation_steps_append— follow after preflight, before the mission.on_complete— follow after the report is written.
What ships with it
22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/templates/environment.md 3.4 KB
- assets/templates/environment.toml 2.2 KB
- assets/templates/gitignore 59 B
- assets/templates/project-readme.md 2.1 KB
- assets/templates/verification-queries.md 2.8 KB
- customize.toml 1.3 KB
- README.md 4.5 KB
- README.vi.md 5.6 KB
- README.zh.md 4.3 KB
- references/adapter-bootstrap.md 5.1 KB
- references/assessment-rubric.md 4.4 KB
- references/bug-report-template.md 2.7 KB
- references/exploration-method.md 7.2 KB
- references/proof-discipline.md 8.8 KB
- references/session-modes.md 9.6 KB
- references/session-note-template.md 3.7 KB
- references/test-plan-authoring.md 5.0 KB
- references/test-plan-intake.md 6.2 KB
- scripts/bootstrap_adapter.py 5.5 KB runs code
- scripts/resolve_customization.py 7.2 KB runs code
- scripts/test_bootstrap_adapter.py 3.5 KB runs code
- scripts/test_resolve_customization.py 7.8 KB runs code
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.
- 16d ago First seen · 230 lines · 178 tokens per session scan C 2cd6417e1142
manual-tester is a skill published in the GitHub repository tronghieu/agent-skills (84 stars, last pushed 2d ago), licensed MIT. It adds 178 tokens to every session and 3,154 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it C with 2 findings (tells the agent never to refuse, 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-expert
Expert-level quality assurance, testing strategies, automation, and QA processes. Use when the user mentions testing, test automation, quality assurance, or Selenium, or when the task involves Testing Types, QA Processes, Test Strategy, or Defect Management.
verification
Full-story verification — infers what the user is building, then verifies the complete flow end-to-end: browser → API → data → response. Triggers on dev server start and 'why isn't this working' signals.
test-master
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.
qa-router
Validation routing and test-failure triage for any repository. Use to select the right gates, author deterministic tests, reproduce CI failures, or diagnose flaky suites.
run-verification
Run the full verification pipeline (lint, unit tests, E2E if UI changed) — invoke after code changes.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.