Borrowing it
Nothing to install: this file belongs to hookdeck/hookdeck-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hookdeck/hookdeck-cli/main/.agents/skills/hookdeck-cli-manual-qa/SKILL.mdgit clone --depth 1 https://github.com/hookdeck/hookdeck-cliWrote 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/hookdeck/hookdeck-cli/hookdeck-cli-manual-qa)<a href="https://agentmods.dev/skills/hookdeck/hookdeck-cli/hookdeck-cli-manual-qa"><img src="https://agentmods.dev/badge/skills/hookdeck/hookdeck-cli/hookdeck-cli-manual-qa/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/hookdeck/hookdeck-cli/hookdeck-cli-manual-qa"><img src="https://agentmods.dev/badge/skills/hookdeck/hookdeck-cli/hookdeck-cli-manual-qa.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 | $0.00108 | $0.03589 |
| Opus 5.5 | $0.00043 | $0.01436 |
| Sonnet 5.5 | $0.00022 | $0.00718 |
| Haiku 4.5 | $0.00011 | $0.00359 |
Grade C, and why
hookdeck-cli-manual-qa scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$SMOKE" && mkdir -p "$SMOKE" How it starts
The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hookdeck CLI — manual QA
Exploratory testing against the live API, in acceptance-test projects, without putting anything else at risk.
This exists because the automated suites cannot cover everything. They run in fixed shapes; a QA pass goes looking for the things nobody thought to assert — wrong success messages, defaults that never get sent, filters that silently do nothing. Every defect this process has found so far was of one kind: a wrong answer that reads like a right one. Look for those specifically.
Safety model — read before running anything
Manual QA runs destructive commands against real projects. Two rules make that survivable, and both are enforced by scripts/hd-testenv.sh:
- Never use the default config. Every command takes
--hookdeck-config "$HD_CONFIG". The operator's ownhookdeck loginis never read or overwritten. This is not hypothetical — a suite run without an isolated config has previously written CI credentials over a working login. - The project is confirmed from the credential, not from the argument. You name the project you expect up front; the guard authenticates, resolves the project, and refuses to hand back a config if it is anything else or is outside the acceptance-test organisation.
Credentials come only from test/acceptance/.env (gitignored, CI test keys), so
the reachable blast radius is the test projects those keys can see.
Before any delete, call hd_assert "$HD_PROJECT" and abort on failure. It is
one cheap line and it catches a config swapped or a project switched mid-run.
If the guard refuses, stop and read the message. It fails closed on purpose; working around it defeats the point.
Record every config file before you start, and check them at the end
The two rules above protect the config the guard hands you. They cannot protect
a config the guard does not know about, and in pass 1 that gap cost the operator
a working config: hookdeck project use honoured --hookdeck-config for reads
but re-derived its own write target, so it overwrote the .hookdeck/config.toml
that happened to be in the working directory and lost its contents (#424).
What ships with it
5 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.
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.
- 1mo ago First seen · 317 lines · 108 tokens per session scan C 19ea19d645f1
hookdeck-cli-manual-qa is a skill published in the GitHub repository hookdeck/hookdeck-cli (366 stars, last pushed yesterday), licensed Apache-2.0. It adds 108 tokens to every session and 3,589 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-25.
Other skills, from other repositories
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
tmux-real-user-testing
A real-user test workflow for Qwen Code's terminal interface, using tmux to drive the program and capture readable screen snapshots. tmux is a tool for running and observing terminal sessions.
agent-reproduce-align
Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen Code under the same scenario, capture HTTP and terminal traces, compare request bodies, tool/function schemas, outputs, and iterate until the reproduced behavior is close enough.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.