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 diagrid-labs/dapr-skills --skill dapr-sharedgit clone --depth 1 https://github.com/diagrid-labs/dapr-skillsWrote 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/diagrid-labs/dapr-skills/dapr-shared)<a href="https://agentmods.dev/skills/diagrid-labs/dapr-skills/dapr-shared"><img src="https://agentmods.dev/badge/skills/diagrid-labs/dapr-skills/dapr-shared/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/diagrid-labs/dapr-skills/dapr-shared"><img src="https://agentmods.dev/badge/skills/diagrid-labs/dapr-skills/dapr-shared.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 | $0.00033 | $0.00148 |
| Opus 5.5 | $0.00013 | $0.00059 |
| Sonnet 5.5 | $0.00007 | $0.00030 |
| Haiku 4.5 | $0.00003 | $0.00015 |
Grade A, and why
dapr-shared 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 8d 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.
What it actually says
Dapr shared reference files
This folder holds content shared by the Dapr Workflow and agent skills in
diagrid-labs/dapr-skills.
Skills reference these files as ../dapr-shared/<file>, so this skill must be
installed next to them. Install all skills with:
npx skills add diagrid-labs/dapr-skills --skill "*"
What ships with it
60 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.
- agent-dapr-yaml-multi.md 4.2 KB
- agent-dapr-yaml-single.md 2.9 KB
- agent-llm-anthropic.md 1.4 KB
- agent-llm-googleai.md 1.6 KB
- agent-llm-ollama.md 1.5 KB
- agent-llm-openai.md 1.3 KB
- agent-logging-python.md 2.2 KB
- agent-metrics-prometheus.md 2.9 KB
- agent-observability-stack.md 4.6 KB
- agent-pubsub-redis.md 2.6 KB
- agent-statestore-memory.md 2.9 KB
- agent-statestore-registry.md 3.3 KB
- agent-statestore-workflow.md 2.0 KB
- agent-tools-dotnet.md 7.5 KB
- agent-tools-python.md 3.7 KB
- agent-tracing-otlp.md 1.8 KB
- agent-tracing-zipkin.md 2.1 KB
- agents/openai.yaml 216 B
- dapr-pubsub-redis.md 756 B
- dapr-pubsub-resiliency.md 1.5 KB
- dapr-pubsub-subscription.md 2.5 KB
- dapr-secretstore-local-env.md 1.9 KB
- dapr-statestore.md 689 B
- dev-dashboard.md 4.8 KB
- dotnet-activity-class.md 2.5 KB
- dotnet-aspire-dapr-wiring.md 11 KB
- dotnet-gitignore.md 226 B
- dotnet-local-http.md 1.9 KB
- dotnet-models.md 1.1 KB
- dotnet-pubsub-handler.md 5.1 KB
- dotnet-pubsub-messaging.md 9.9 KB
- dotnet-pubsub-publisher.md 6.6 KB
- dotnet-pubsub-subscriber-declarative.md 4.2 KB
- dotnet-pubsub-subscriber-programmatic.md 5.2 KB
- dotnet-workflow-class.md 11 KB
- dotnet-workflow-endpoints.md 11 KB
- migrate-report-format.md 3.8 KB
- prereq-check-aspire-cli.md 964 B
- prereq-check-csharp-lsp.md 928 B
- prereq-check-dapr-agents-sdk.md 1.8 KB
- prereq-check-dapr-cli.md 913 B
- prereq-check-docker-podman.md 753 B
- prereq-check-dotnet-sdk.md 548 B
- prereq-check-llm-provider.md 2.2 KB
- prereq-check-pyright.md 279 B
- prereq-check-python-lsp.md 939 B
- prereq-check-python-sdk.md 772 B
- prereq-check-uv.md 222 B
- prereq-detect-os.md 1.4 KB
- pubsub-concepts.md 12 KB
- pubsub-dapr-yaml.md 2.4 KB
- pubsub-local-http.md 2.3 KB
- pubsub-placeholders.md 7.3 KB
- pubsub-run-doc.md 2.8 KB
- python-local-http.md 1.6 KB
- python-pubsub-handler.md 3.6 KB
- python-pubsub-project.md 1.8 KB
- python-pubsub-publisher.md 5.9 KB
- python-pubsub-subscriber-declarative.md 2.8 KB
- python-pubsub-subscriber-programmatic.md 2.8 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.
- 8d ago Changed · -25 tokens per session 9e1ccee65147
- 12d ago Changed · +1 tokens per session 6799691b54e3
- 13d ago First seen · 16 lines · 57 tokens per session scan A 2b22466b648a
dapr-shared is a skill published in the GitHub repository diagrid-labs/dapr-skills (13 stars, last pushed 8d ago), licensed MIT. It adds 33 tokens to every session and 148 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-13.
Other skills, from other repositories
agent-orchestrator
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
<skill-name>
A template for defining a coding-agent skill, including its title, trigger situations, overview, workflow, common mistakes, and optional references.
ai-loop
Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.
spec-writing
A method for writing a software specification: a document that records decisions, reasons, boundaries, and ways to judge whether implementation succeeded. It first checks whether important unknowns require user clarification or technical research.
onboarding-unknown-codebase
A method for quickly understanding an unfamiliar codebase, meaning a software project whose structure and behavior you do not yet know. It builds a project map by examining overview files, directories, and one main execution path.
commit-message
A guide for writing clear, traceable Git commit messages using the Conventional Commits format, which labels changes such as features, bug fixes, documentation, and refactoring.