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 javiarmesto/ALDC-AL-Development-Collection --skill extension-manifestgit clone --depth 1 https://github.com/javiarmesto/ALDC-AL-Development-CollectionWrote 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/javiarmesto/aldc-al-development-collection/extension-manifest)<a href="https://agentmods.dev/skills/javiarmesto/aldc-al-development-collection/extension-manifest"><img src="https://agentmods.dev/badge/skills/javiarmesto/aldc-al-development-collection/extension-manifest/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/javiarmesto/aldc-al-development-collection/extension-manifest"><img src="https://agentmods.dev/badge/skills/javiarmesto/aldc-al-development-collection/extension-manifest.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 | $0.00080 | $0.01976 |
| Opus 5 | $0.00040 | $0.00988 |
| Sonnet 5 | $0.00016 | $0.00395 |
| Haiku 4.5 | $0.00008 | $0.00198 |
Grade A, and why
skill-manifest 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.
This is a copy
91% identical to skill-manifest — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Extension Manifest Generator
Generates a handoff manifest at the end of the ALDC pipeline, enabling CIRCE and/or DELFOS to consume the extension's published surface without sharing a workspace.
Trigger
This skill activates after the Conductor pipeline completes successfully (all sub-agents finalized, all HITL gates passed). The agent MUST NOT generate the manifest until the extension compiles and all tests pass.
The skill reads from:
- The
al-spec.md(or equivalent spec file) for the completed extension - The actual
.alsource files in the project directory - The
app.jsonfor publisher, version, and extension metadata
The skill outputs a single {extension-name}-manifest.md file in the project root or a designated output/ directory.
Interactive Gate (HITL — Required)
Before generating the manifest, the agent MUST ask the user:
The extension pipeline is complete. I can generate a handoff manifest
for consumption by other frameworks in the ecosystem.
Who will consume this manifest?
(a) CIRCE — to build a Copilot Studio agent against this extension
(b) DELFOS — to build a Power BI dashboard against this extension's data
(c) Both CIRCE and DELFOS
Which option? (a / b / c)
The agent waits for the user's response. No manifest is generated without explicit selection.
If the user selects (c) Both, the agent generates a single unified manifest containing all sections for both targets, clearly labeled.
Additional Interactive Gate — CIRCE Connection Details
When the target includes CIRCE (options a or c), the agent MUST ask:
To generate the CIRCE connection section, I need your BC environment details:
BC Environment name: ___
Company name: ___
MCP Configuration Code (from Page 8351): ___
If you haven't created the MCP configuration yet, I can generate the
manifest with placeholder values that you'll fill in after configuring
Page 8351.
Manifest Structure
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 · 185 lines · 80 tokens per session scan A 37fc4e4f3793
skill-manifest is a skill published in the GitHub repository javiarmesto/ALDC-AL-Development-Collection (104 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 1,976 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to skill-manifest, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
android-data-persistence
Use when implementing local data storage with Room, DataStore, or offline-first patterns. Covers entities, DAOs, migrations, Paging3, and the repository pattern for data management.
android-device-testing
Use when writing or debugging instrumented tests (Espresso, UI Automator, Compose test rules), using ADB, managing emulators, or inspecting UI with Layout Inspector.
ci-cd-and-automation
Use when setting up or improving CI/CD pipelines for Android. Covers sequential quality gates, Gradle caching, emulator testing in CI, feature flags, and automated deployment to Play Store.
security-and-hardening
Use when handling sensitive data, authentication, network communication, or before shipping to the Play Store. Three-tier framework (Always Do, Ask First, Never Do) with Android-specific security patterns.
api-and-interface-design
Use when designing interfaces between layers (Repository, UseCase, API client) or defining data contracts. Covers Retrofit interfaces, Room DAOs, Kotlin sealed classes, and backward compatibility.
deprecation-and-migration
Use when deprecating APIs, bumping minSdk, migrating libraries (AndroidX, Compose, Kotlin versions), or removing legacy code. Covers Kotlin @Deprecated annotation, strangler pattern, and incremental migration.