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 enmanuelmag/agent-harness-kit --skill ahk-testgit clone --depth 1 https://github.com/enmanuelmag/agent-harness-kitWrote 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/enmanuelmag/agent-harness-kit/ahk-test)<a href="https://agentmods.dev/skills/enmanuelmag/agent-harness-kit/ahk-test"><img src="https://agentmods.dev/badge/skills/enmanuelmag/agent-harness-kit/ahk-test.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00871 |
| Opus 5 | $0.00018 | $0.00436 |
| Sonnet 5 | $0.00007 | $0.00174 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
ahk-test 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Provider Delegation Guidance
- Sequential: Delegate only bounded, independent work; retain decisions and the final synthesis in the parent thread.
- Parallel: Delegate independent work in parallel when useful, then wait for every delegated result before continuing.
- Context Transfer: Give every delegated task a self-contained objective, scope, relevant context, restrictions, and output contract.
- Wait For Completion: Wait for the delegated result, then consolidate its findings in the parent thread.
- Inspect Progress: In the interactive CLI, use /agent to inspect delegated threads when needed.
You are in lightweight test mode. The testing objective: $ARGUMENTS
If
$ARGUMENTSis empty, ask the user what behavior they want tested before doing anything else.
Rules
- NO MCP calls — no tasks., no actions., no tasks.acceptance.update
- NO harness task creation or state changes
- Production files are READ-ONLY unless the user explicitly authorizes production changes
- Do not install dependencies or change test configuration without explicit authorization
- Run health.sh only when the user requests full harness verification or it is the repository's relevant test entrypoint; never use it instead of the focused test
- Do not delete, weaken, skip, or rewrite existing expectations to make the suite pass
- Do not add
.only,.skip,.todo, or snapshots by default - A test file is not evidence until its command has run
Process
-
Invoke Explorer as a subagent with this instruction:
"Read-only test investigation — no MCP harness and no task creation. Testing objective:
$ARGUMENTS. Read the complete unit under test, its relevant types and imports, the project's test scripts/configuration, and one or two nearby tests. Identify: observable behaviors, the source of each expected result, project conventions, likely test level, files a test would touch, and genuine ambiguities. Do not write files." -
Build a concise test matrix with these columns:
- Behavior
- Input or action
- Expected observable result
- Test level
- Source of expectation
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.
- 2d ago Changed · +9 lines dee194b63676
- 4d ago First seen · 62 lines · 36 tokens per session scan A 2f6f656c3e42
ahk-test is a skill published in the GitHub repository enmanuelmag/agent-harness-kit (180 stars, last pushed 2d ago), licensed Apache-2.0. It adds 36 tokens to every session and 871 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other skills, from other repositories
review-prs
Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…
tool-abuse-detection
Detect tool misuse and unexpected code execution via dialogue testing. Use when the agent exposes file, code-execution, or network tools.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
langbot-testing
Test LangBot WebUI and core product flows with an automated browser and backend logs. Use when validating the configured LangBot frontend, pipeline Debug Chat, model provider setup and test buttons, bot and knowledge-base UI flows, or troubleshooting failed LangBot end-to-end tests.
benchmark-design
Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.