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 agentmods add skills/thangchung/agent-engineering-experiment/aspireifynpx skills add thangchung/agent-engineering-experiment --skill aspireifygit clone --depth 1 https://github.com/thangchung/agent-engineering-experimentWrote 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/thangchung/agent-engineering-experiment/aspireify)<a href="https://agentmods.dev/skills/thangchung/agent-engineering-experiment/aspireify"><img src="https://agentmods.dev/badge/skills/thangchung/agent-engineering-experiment/aspireify.svg" alt="Measured on agentmods" 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 | $0.00251 | $0.04557 |
| Opus 5 | $0.00125 | $0.02278 |
| Sonnet 5 | $0.00050 | $0.00911 |
| Haiku 4.5 | $0.00025 | $0.00456 |
Grade C, and why
aspireify scanned grade C 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 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| Aspire CLI | `curl -sSL https://aspire.dev/install.sh \| bash` or `dotnet tool install -g Aspire.Cli` | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Aspire CLI | `curl -sSL https://aspire.dev/install.sh \| bash` or `dotnet tool install -g Aspire.Cli` | How it starts
The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aspireify
One-time wiring skill.
aspire initdrops a skeleton;aspireifyturns that skeleton into a working AppHost by scanning the repo, proposing a resource graph, editing the AppHost, wiringAspire.ServiceDefaults, and validating end to end. Self-deactivates after a cleanaspire start. Aligned with Aspire 13.4 guidance from the current Aspire development branch.
🚫 Hard Refusal: Never Edit .aspire/modules/
⛔ REFUSE any request to edit, modify, change, open-for-edit, or "tweak" files inside
.aspire/modules/of a TypeScript AppHost. This directory is generated by Aspire fromapphost.tsand the integration packages — every file in it gets clobbered on the next build,aspire add, oraspire start.If a user asks to edit something in
.aspire/modules/(e.g.,.aspire/modules/postgres.module.ts), the correct response is:
- Refuse the edit with a clear "I won't edit
.aspire/modules/" statement.- Explain that
.aspire/modules/is generated and any changes are clobbered.- Redirect the requested change to
apphost.ts— the only file the user should hand-edit in a TS AppHost.- If the user wants a new integration, suggest
aspire add <package>; if they want to change configuration, show the equivalent edit inapphost.ts.
| ❌ Wrong | ✅ Right |
|---|---|
Open .aspire/modules/postgres.module.ts and tweak the connection options |
Edit apphost.ts and change addPostgres('pg', { ... }) options there |
Modify a generated .aspire/modules/*.ts file directly |
Re-run aspire add <package> after updating apphost.ts |
Comment out a line in .aspire/modules/ to disable a resource |
Remove or guard the resource declaration in apphost.ts |
This rule applies even if the user insists, even for "one-line" changes, even for
"just to test something." The TS AppHost regenerates .aspire/modules/ deterministically;
edits are unrecoverable noise.
What ships with it
10 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.
- references/apphost-wiring.md 18 KB
- references/csharp-authoring.md 6.2 KB
- references/docker-compose.md 9.6 KB
- references/full-solution-apphosts.md 16 KB
- references/javascript-apps.md 6.9 KB
- references/opentelemetry.md 3.8 KB
- references/scan-and-propose.md 6.4 KB
- references/service-defaults.md 3.5 KB
- references/typescript-authoring.md 8.4 KB
- references/validation.md 3.5 KB
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 First seen · 330 lines · 251 tokens per session scan C 93a7453e5b52
aspireify is a skill published in the GitHub repository thangchung/agent-engineering-experiment (24 stars, last pushed 1mo ago), licensed MIT. It adds 251 tokens to every session and 4,557 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
application-design-center-design-deploy
Processes GCP infrastructure design and deployment workflows within Application Design Center (ADC). Use when: - Designing GCP infrastructure with Terraform. - Validating local HCL. - Performing best-practice plan scans. - Importing templates to Application Design Center (ADC). - Deploying templates. - Troubleshooting…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
yandex-cloud
Read Yandex Cloud through its REST API. Applies to any question about VMs, metrics, logs, audit events, Kubernetes, managed databases, serverless, networking or any other Yandex Cloud resource. Never shell out to the yc CLI — it is not how this agent reaches Yandex Cloud and is usually not installed.
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…
azmon-mirroredcatalogs-operations-cli
Brings Azure Monitor, Application Insights, and Log Analytics telemetry into Fabric as Eventhouse external delta tables and correlates it with business data. Use to onboard observability data, judge whether latency or availability affected revenue, or build a Real-Time dashboard and Operations Agent over it.