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.
git clone --depth 1 https://github.com/bendaamerahmed/backstage-idp-pluginWrote 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/agents/bendaamerahmed/backstage-idp-plugin/backstage-fullstack-developer)<a href="https://agentmods.dev/agents/bendaamerahmed/backstage-idp-plugin/backstage-fullstack-developer"><img src="https://agentmods.dev/badge/agents/bendaamerahmed/backstage-idp-plugin/backstage-fullstack-developer/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/agents/bendaamerahmed/backstage-idp-plugin/backstage-fullstack-developer"><img src="https://agentmods.dev/badge/agents/bendaamerahmed/backstage-idp-plugin/backstage-fullstack-developer.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 | $0.00093 | $0.13801 |
| Opus 5.5 | $0.00037 | $0.05520 |
| Sonnet 5.5 | $0.00019 | $0.02760 |
| Haiku 4.5 | $0.00009 | $0.01380 |
Grade A, and why
backstage-fullstack-developer scanned grade A 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 1mo 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.
Enumerates other installed skillslowAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
Before inventing a workflow, inspect available skills. Prefer a maintained skill for repeated procedures. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 2,091 lines — stays where its author put it; the contents beside it link to each section on GitHub.
0. Version Baseline
This definition was verified against Backstage as of August 2026. Treat the facts below as a starting hypothesis with a shelf life, never as settled truth: Backstage ships a mainline release every month, so this section goes stale fast.
| Fact | Value as verified (Aug 2026) |
|---|---|
| Current stable release line | v1.53.x |
| Release cadence | Mainline monthly, on the Tuesday before the third Wednesday; next line weekly on Tuesdays |
| Supported Node.js | Exactly two adjacent even majors — 22 and 24 (policy since v1.46.0) |
| Frontend system | New Frontend System is the default for newly created apps since v1.49.0; create-app --next was replaced by create-app --legacy |
| Backend system | New Backend System is the established default; legacy backend composition is migration-only |
| UI library | @backstage/ui ("BUI", formerly Canon) — core components and entity cards are migrating off Material UI |
| Deprecation policy | A deprecation must ship in at least one mainline release before removal |
| Community plugins | Live in the separate backstage/community-plugins repo under @backstage-community/plugin-* |
Rule: before implementing anything version-sensitive, verify the repository's actual installed versions first (§5.1, §5.2), and re-check official documentation when the repository's release line differs from the table above. If the repository is on a release line older than this table, the table is wrong for that repository and the repository wins.
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.
- 1mo ago First seen · 2,091 lines · 93 tokens per session scan A 342a6a7ed211
backstage-fullstack-developer is an agent published in the GitHub repository bendaamerahmed/backstage-idp-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 13,801 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
ash-resource-designer
Ash resource architect — designs resources the "Ash Way" with built-in changes, validations, types, and policy checks before hand-rolling. Use proactively when planning new resources or extending existing ones.
liveview-architect
LiveView architecture specialist - component structure, real-time patterns, streams vs assigns, async patterns. Use proactively when planning interactive features.
security-analyzer
Security audit specialist for Elixir/Phoenix - authentication, authorization, input validation, OWASP vulnerabilities. Use proactively when implementing auth or handling user input.
call-tracer
Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.
oban-specialist
Oban worker specialist - reviews idempotency, error handling, and production safety. Use proactively when implementing or reviewing background jobs.
otp-advisor
OTP patterns specialist - GenServer, Supervisor, Agent, Task, Registry, ETS. Use proactively when deciding if you need OTP abstractions or simpler solutions.