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-use-casesgit 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-use-cases)<a href="https://agentmods.dev/skills/enmanuelmag/agent-harness-kit/ahk-use-cases"><img src="https://agentmods.dev/badge/skills/enmanuelmag/agent-harness-kit/ahk-use-cases/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-use-cases"><img src="https://agentmods.dev/badge/skills/enmanuelmag/agent-harness-kit/ahk-use-cases.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.00483 |
| Opus 5 | $0.00015 | $0.00242 |
| Sonnet 5 | $0.00006 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
ahk-use-cases 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 3d 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 — 34 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.
Purpose
Guide a lightweight, iterative product-discovery conversation. Do not choose a stack, library, API, architecture, or implementation plan.
Read the discovery workflow before the conversation and the use-case template before saving.
Discovery
Ask one follow-up question at a time. Establish the user and their goal, current and desired flow, trigger, happy path, variants and failures, business rules, boundaries, exclusions, assumptions, risks, dependencies, priority, success signal, and observable acceptance criteria. Separate confirmed decisions from open questions and do not invent either.
Save and iterate
When the user explicitly asks to save the agreed result, use the specification MCP tools. Create or update docs/specs/<slug>.md through structured tools only. Use specs.list before creating, specs.get for the selected specification, and specs.validate after every write. A use-case becomes approved only after the user explicitly approves it.
If the user changes an approved use-case, explain the affected technical specifications, update the use-case, and let the MCP transition linked technical specs to needs-reconciliation. Keep the conversation iterative; later messages refine the same specification unless the user clearly starts another initiative.
Handoff
Offer ahk-use-case-tech only when the use case is approved and the user asks for technical design. The saved body follows the template and covers problem and value, actors, scope and exclusions, current and desired flows, cases and edge cases, rules, dependencies and risks, assumptions/open decisions, acceptance criteria, and change log.
What ships with it
2 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.
- 3d ago Changed · +9 lines df012f0519f6
- 4d ago First seen · 25 lines · 30 tokens per session scan A a9fcc43f79d2
ahk-use-cases is a skill published in the GitHub repository enmanuelmag/agent-harness-kit (181 stars, last pushed 2d ago), licensed Apache-2.0. It adds 30 tokens to every session and 483 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 2026-09-05.
Other skills, from other repositories
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
meta-meeting-to-workflow
Use this meta-skill instead of answering directly when the user has meeting notes, transcripts, recordings, or rough discussion notes and wants them converted into decisions, owners, follow-ups, tasks, issues, or shareable minutes through multi-skill orchestration.
meta-issue-to-pr-autopilot
Triages an issue, delegates the fix to sub-agent, drafts a PR description with summarize, and opens the PR via gh. Best used on small, well-scoped issues with clear acceptance criteria.
meta-github-pr-watch-digest
Inspect the user's open GitHub PRs / failing CI / new issues via gh, summarize into 3 buckets (to-review / awaiting-me / CI-red), and persist follow-ups to memory.
secretary
Workspace and research management — dispatch analyses, monitor running agents, manage workspaces and threads.
ceo-setup
One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.