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 Xakki/ai-agents-skills --skill agent-config-testgit clone --depth 1 https://github.com/Xakki/ai-agents-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/xakki/ai-agents-skills/agent-config-test)<a href="https://agentmods.dev/skills/xakki/ai-agents-skills/agent-config-test"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/agent-config-test/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/xakki/ai-agents-skills/agent-config-test"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/agent-config-test.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 | $0.00071 | $0.02543 |
| Opus 5 | $0.00036 | $0.01272 |
| Sonnet 5 | $0.00014 | $0.00509 |
| Haiku 4.5 | $0.00007 | $0.00254 |
Grade D, and why
agent-config-test scanned grade D 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| Wrapper prefix | `env FOO=1 pytest`, `sudo docker …` | same | Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
approves `devbox run rm -rf .`. How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test agent configuration
setup-claude writes agent config. This skill proves it behaves.
Two lanes, because only one of them is executable:
| Lane | Tool | What it proves |
|---|---|---|
| Hook behaviour | test-hooks.sh |
Real assertion: this payload => this exit code |
| Settings shape | lint-settings.sh |
Static only. It never proves a deny rule works |
There is no evaluator for allow/ask/deny rules — nothing to shell out to.
Never report permission rules as "tested"; they are linted.
Happy path
skills/agent-config-test/test-hooks.sh .claude/hooks/guard-bash.sh cases/guard-bash.tsv
skills/agent-config-test/lint-settings.sh /path/to/project
Cases file — <expected-exit>TAB<command>[TAB<label>], 2 = must block, 0 =
must allow, \n decodes to a real newline. Start from
cases/guard-bash.tsv and keep its bypass block verbatim.
Other events: --event PostToolUse --tool Edit, or put raw JSON in the payload
column (any line starting with {). Per-event stdin fields and valid matcher
values → reference.md.
test-hooks.sh maps the plain-text payload column into the right
tool_input field by tool: command for Bash/PowerShell, file_path for
Read/Edit/Write, path for Grep/Glob, notebook_path for NotebookEdit, url
for WebFetch — with an explicit --field NAME override for anything else. For
a file-path hook (e.g. a lint gate on Edit), see
cases/check-file.tsv.
The three rules that make this worth running
1. Test BOTH directions, always. Block-cases alone certify a guard that also
eats grep -rn pytest tests/. Every real bug found in these guards was a false
positive: dd matching inside add, rm inside confirm. A suite without
must-allow cases is worse than no suite — it manufactures confidence.
2. Cases live in a FILE, never on the command line. A guard matches command
TEXT, so a runner invoked as for c in "docker compose up" ... trips the very
guard under test and the suite blocks itself. This is not hypothetical; it is
the first thing that happens.
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.
- 11d ago First seen · 186 lines · 71 tokens per session scan D d50bbccef23e
agent-config-test is a skill published in the GitHub repository Xakki/ai-agents-skills (6 stars, last pushed 20d ago), licensed MIT. It adds 71 tokens to every session and 2,543 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
taiyi-dev
A software-development stage that implements planned tasks using test-driven development, or TDD: write a failing test, make it pass, then improve the code. It checks the task plan, dependencies, file boundaries, and required completion evidence.
taiyi-test
A project workflow skill for verifying an implementation and producing a TEST.md record. TDD means writing a failing test, implementing the change, and then making the test pass; this skill checks that process and other regression cases.
sc-skill
Capture deterministic macOS screenshots for testing, docs, release notes, and marketing assets. Use when asked to automate app screenshots, batch-generate screenshot sets, standardize window sizing/composition, or choose between Peekaboo and native macOS screenshot tooling.
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.
agent-session-format-check
Verify agent session format compatibility for Agent Sessions. Use when any agent CLI updates, when monitoring flags drift, or when bumping max verified versions (fixtures + docs + tests). Covers session schema, usage/limits tracking, storage backends, and discovery path contracts for all supported agents.
ag-referencia-tdd
TDD canonico Red-Green-Refactor — pipeline obrigatorio teste-primeiro. Reference skill carregada on-demand pelo modo --tdd da ag-1-construir.