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-consultantgit 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-consultant)<a href="https://agentmods.dev/skills/enmanuelmag/agent-harness-kit/ahk-consultant"><img src="https://agentmods.dev/badge/skills/enmanuelmag/agent-harness-kit/ahk-consultant/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/enmanuelmag/agent-harness-kit/ahk-consultant"><img src="https://agentmods.dev/badge/skills/enmanuelmag/agent-harness-kit/ahk-consultant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 29 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 36 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00035 | $0.00464 |
| Opus 5 | $0.00017 | $0.00232 |
| Sonnet 5 | $0.00007 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
ahk-consultant 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 4d 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 — 38 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 consultation mode. The user's topic: $ARGUMENTS
Rules
- NO MCP calls — no tasks., no actions.
- NO health.sh
- NO builder, NO reviewer
- Create files ONLY if user explicitly asked to save the output
Process
-
Invoke Explorer as a subagent:
"Read-only context gathering — no MCP harness. The user wants technical advice on:
$ARGUMENTS. Map the relevant codebase — existing patterns, current implementation, relevant dependencies. Return findings as plain structured text." -
Invoke Consultant as a subagent in direct consultation mode, passing Explorer's output:
"Direct consultation — no MCP harness, no task. User's topic:
$ARGUMENTS. Explorer found: [explorer output]. Provide structured technical advice. The provider has already injected available skills into your context — check what skills you are aware of, identify which are relevant to this topic, and reference them explicitly in your advice. If no installed skills seem relevant to the topic, recommend runningnpx autoskillsto fetch appropriate skill packs." -
Synthesize a final response for the user.
Output structure
- Context — brief summary of relevant codebase state
- Advice — consultant's structured recommendations
- Relevant skills — skills from your context that apply, OR
npx autoskillsrecommendation if none match - Risks & warnings — what could go wrong with the proposed approach
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.
- 4d ago Changed · +9 lines 455daebc047d
- 11d ago First seen · 29 lines · 35 tokens per session scan A 2a3c77590530
ahk-consultant is a skill published in the GitHub repository enmanuelmag/agent-harness-kit (181 stars, last pushed 3d ago), licensed Apache-2.0. It adds 35 tokens to every session and 464 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 2026-08-30.
Other skills, from other repositories
taobao-search
A tool for searching products on Taobao, Alibaba’s consumer shopping marketplace, by opening its search page in the Taobao app. It supports product, brand, price-limit, comparison, and new-product searches.
OpenCode
Frames OpenCode as an operator-controlled coding lane for bounded implementation or review work inside a real repository.
ordercli
Foodora-only CLI for checking past orders and active order status (Deliveroo WIP).
opencode
Use when working with a model-agnostic terminal AI coding agent that uses opencode.json for declarative configuration — MCP servers, custom commands, agent routing, skills. OpenCode: configuration-as-code terminal AI coding agent with multi-model support.
eliza-cloud-buy-domain
Use whenever a user wants to register or buy a custom domain for an Eliza Cloud app — including in the same request as building the app ("build me X and put it on Y.com"). Uses Cloudflare as registrar after explicit user confirmation, paid from the user's existing cloud credit balance. Pairs with build-monetized-app…
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…