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 Ampli-Group/agentic-mobile-blueprint --skill template-releasegit clone --depth 1 https://github.com/Ampli-Group/agentic-mobile-blueprintWrote 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/ampli-group/agentic-mobile-blueprint/template-release)<a href="https://agentmods.dev/skills/ampli-group/agentic-mobile-blueprint/template-release"><img src="https://agentmods.dev/badge/skills/ampli-group/agentic-mobile-blueprint/template-release/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/ampli-group/agentic-mobile-blueprint/template-release"><img src="https://agentmods.dev/badge/skills/ampli-group/agentic-mobile-blueprint/template-release.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 | $0.00040 | $0.01053 |
| Opus 5.5 | $0.00016 | $0.00421 |
| Sonnet 5.5 | $0.00008 | $0.00211 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade B, and why
template-release scanned grade B with 1 finding 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 2mo 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- **Upgrade notes cover shared infrastructure only.** App scaffold files (`mobile/app/`, example screens, demo Maestro flows) are replaced by consuming projects — never mention them in upgrade notes. How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Process
This template uses semver (MAJOR.MINOR.PATCH) for tracking purposes only.
CI/CD pipelines are not gated on version tags — they trigger on merges to main.
| Bump | When |
|---|---|
| PATCH (0.1.x) | Bug fixes, security patches, dependency updates — no API or skill changes |
| MINOR (0.x.0) | New features, new skills, new integrations — backwards-compatible |
| MAJOR (x.0.0) | Breaking changes to file structure, API contracts, or required env vars |
Step 1 — Decide the next version
- Read
TEMPLATE_VERSIONto get the current version. - Review changes since the last tag:
git log $(git describe --tags --abbrev=0)..HEAD --oneline git diff $(git describe --tags --abbrev=0)..HEAD --stat - Apply the semver rules above to pick
MAJOR.MINOR.PATCH.
Step 2 — Write upgrade notes
Create .agents/skills/template-upgrade/vMAJOR.MINOR.PATCH.md using the template below.
Every section is required. Use "None" for empty sections — never omit them.
What belongs in upgrade notes
Only document changes that consuming projects can and should pull in:
| Include | Exclude |
|---|---|
supabase/functions/_shared/ utilities |
mobile/app/ screens and components |
.agents/skills/ (new or updated skills) |
maestro/ YAML test flows |
supabase/migrations/ shared schema |
Example / demo screens |
Build config (eas.json, app.json keys) |
Any file a project is expected to replace |
| New required env vars | Internal refactors with no consumer impact |
| Dependency version bumps | |
AGENTS.md changes agents should adopt |
Rule of thumb: if a project that forked this template has almost certainly replaced the file already, do not mention it.
# vMAJOR.MINOR.PATCH — <one-line summary>
Released: YYYY-MM-DD
## Breaking Changes
<!-- What existing projects MUST change before upgrading. -->
<!-- Format: "**`path/to/file`** — what changed and why" -->
None
## New Features
<!-- New shared skills, utilities, or integrations. -->
<!-- Do NOT include app-scaffold additions (screens, demo flows, etc.). -->
None
## Improvements
<!-- Reliability, performance, or DX improvements to shared infrastructure. -->
None
## Bug Fixes
<!-- Defects corrected in shared code. -->
None
## Dependency Updates
<!-- Package version bumps worth noting. -->
None
## Upgrade Instructions
Step-by-step for a project that already uses a previous version of this template.
1. Copy changed shared files / snippets as described in each section above.
2. Update any env vars listed under Breaking Changes.
3. Run `mise run configure` if new env vars were added.
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.
- 2mo ago First seen · 133 lines · 40 tokens per session scan B 30448c73e4b8
template-release is a skill published in the GitHub repository Ampli-Group/agentic-mobile-blueprint (4 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 1,053 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
template-release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| template-releaseAmpli-Group/agentic-mobile-blueprint | Skill | 4 | 3mo ago | MIT | B | 40 | Claude Code, Codex |
| manage-prswataru-maeda/react-native-boilerplate | Skill | 524 | 5d ago | MIT | A | 53 | Claude Code, Codex |
| playground-snapshot-releasemastra-ai/mastra | Skill | 29k | yesterday | none | A | 114 | Claude Code, Codex |
| pr-snapshot-releasemastra-ai/mastra | Skill | 29k | yesterday | none | A | 88 | Claude Code, Codex |
| agent-framework-py-releasemicrosoft/agent-framework | Skill | 15k | yesterday | MIT | A | 102 | Claude Code, Codex |
| release-publishrohitg00/ai-engineering-from-scratch | Skill | 77k | yesterday | MIT | A | 9 | Claude Code, Codex |
| release-reviewrohitg00/ai-engineering-from-scratch | Skill | 77k | yesterday | MIT | A | 7 | Claude Code, Codex |