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/andr-ca/agentharness/dependency-injectionnpx skills add andr-ca/agentharness --skill dependency-injectiongit clone --depth 1 https://github.com/andr-ca/agentharnessWhat 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 | $0.00047 | $0.00739 |
| Opus 5 | $0.00023 | $0.00369 |
| Sonnet 5 | $0.00009 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
dependency-injection 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 2d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Injection
One rule: depend on abstractions, receive them via constructor, never create them internally.
The Pattern
# BAD — hard to test, tightly coupled
class OrderService:
def __init__(self):
self.db = Database() # creates its own dependency
self.email = EmailClient() # can't inject fakes in tests
# GOOD — testable, decoupled
class OrderService:
def __init__(self, db: Database, email: EmailClient) -> None:
self.db = db
self.email = email
// BAD
class OrderService {
private db = new Database(); // hidden dependency
}
// GOOD
class OrderService {
constructor(private db: Database, private email: EmailClient) {}
}
Rules
| Do | Don't |
|---|---|
| Inject dependencies via constructor | Create dependencies with new inside a class |
| Depend on interfaces/protocols | Depend on concrete types when an abstraction exists |
| Make dependencies explicit | Use service locators (Container.get(...)) inside business logic |
| Keep constructors simple — no logic | Do work in __init__/constructors |
| Use fakes/stubs in tests | Patch global singletons in tests |
When to Use a DI Container
Use a container (FastAPI's Depends, tsyringe, Wire for Go) when:
- The object graph has 3+ levels of nesting
- You need lifetime management (singleton vs. transient vs. scoped)
- You need request-scoped dependencies (e.g., database sessions per HTTP request)
Don't use a container for:
- Small scripts or utilities (manual wiring is simpler and clearer)
- Value objects (DTOs, records) — they carry data, not behavior
- Stateless pure functions
Lifetimes
| Lifetime | When to use | Example |
|---|---|---|
| Singleton | Shared state across the app; expensive to create | DatabasePool, ConfigLoader |
| Scoped | One instance per request/unit of work | DbSession, UserContext |
| Transient | Stateless; cheap to create | EmailFormatter, Validator |
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.
- 2d ago First seen · 99 lines · 47 tokens per session scan A be9157aa168f
dependency-injection is a skill published in the GitHub repository andr-ca/agentharness (1 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 739 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 2026-08-31.
Other skills, from other repositories
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
digital-health-clinical-asr-finetune
Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).
doca-compress
Use this skill for hands-on DOCA Compress programming on a BlueField DPU, ConnectX NIC, or host with DOCA — enabling compress-deflate, decompress-deflate, decompress-lz4-stream, or decompress-lz4-block tasks on a docacompress context (the hardware supports DEFLATE both directions plus LZ4 decompress; LZ4 encode is NOT…