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 SalesforceAIResearch/agentforce-adlc --skill agentforce-generategit clone --depth 1 https://github.com/SalesforceAIResearch/agentforce-adlcWrote 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/salesforceairesearch/agentforce-adlc/agentforce-generate)<a href="https://agentmods.dev/skills/salesforceairesearch/agentforce-adlc/agentforce-generate"><img src="https://agentmods.dev/badge/skills/salesforceairesearch/agentforce-adlc/agentforce-generate.svg" alt="Measured on agentmods" 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 | $0.00186 | $0.14072 |
| Opus 5 | $0.00093 | $0.07036 |
| Sonnet 5 | $0.00037 | $0.02814 |
| Haiku 4.5 | $0.00019 | $0.01407 |
Grade A, and why
agentforce-generate 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- tool: ["curl"] The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- assets/agent-spec-template.md 6.1 KB
- assets/agents/hello-world.agent 1.9 KB
- assets/agents/knowledge-grounded.agent 5.6 KB
- assets/agents/local-info-agent-annotated.agent 17 KB
- assets/agents/order-service.agent 12 KB
- assets/agents/production-faq.agent 3.9 KB
- assets/agents/production-faq.bundle-meta.xml 161 B
- assets/agents/README.md 2.6 KB
- assets/agents/router-first.agent 5.6 KB
- assets/agents/simple-qa.agent 1.9 KB
- assets/agents/template-multi-subagent.agent 5.4 KB
- assets/agents/template-single-subagent.agent 2.6 KB
- assets/agents/verification-gate.agent 11 KB
- assets/agents/voice-knowledge-grounded.agent 8.2 KB
- assets/agents/voice-service-agent.agent 4.6 KB
- assets/bundle-meta.xml 808 B
- assets/invocable-apex-template.cls 6.9 KB
- assets/patterns/action-callbacks.agent 4.6 KB
- assets/patterns/advanced-input-bindings.agent 7.0 KB
- assets/patterns/bidirectional-routing.agent 5.6 KB
- assets/patterns/critical-input-collection.agent 12 KB
- assets/patterns/delegation-routing.agent 6.4 KB
- assets/patterns/lifecycle-events.agent 4.7 KB
- assets/patterns/llm-controlled-actions.agent 5.1 KB
- assets/patterns/multi-step-workflow.agent 10 KB
- assets/patterns/open-gate-routing.agent 12 KB
- assets/patterns/procedural-instructions.agent 4.8 KB
- assets/patterns/prompt-template-action.agent 6.7 KB
- assets/patterns/README.md 11 KB
- assets/patterns/system-instruction-overrides.agent 11 KB
- README.md 4.4 KB
- references/action-prompt-templates.md 5.7 KB
- references/actions-reference.md 30 KB
- references/agent-access-guide.md 2.9 KB
- references/agent-design-and-spec-creation.md 54 KB
- references/agent-metadata-and-lifecycle.md 30 KB
- references/agent-script-core-language.md 45 KB
- references/agent-subagent-map-diagrams.md 10 KB
- references/agent-user-setup.md 28 KB
- references/agent-validation-and-debugging.md 44 KB
- references/architecture-patterns.md 10 KB
- references/complex-data-types.md 3.9 KB
- references/data-library-reference.md 41 KB
- references/deploy-reference.md 6.7 KB
- references/discover-reference.md 4.3 KB
- references/examples.md 13 KB
- references/feature-validity.md 2.1 KB
- references/instruction-resolution.md 21 KB
- references/known-issues.md 25 KB
- references/mcp-management-reference.md 38 KB
- references/optimization-pattern-1-data-flow.md 4.3 KB
- references/optimization-pattern-2-deterministic-logic.md 4.1 KB
- references/optimization-pattern-3-reference-syntax.md 3.0 KB
- references/optimization-pattern-4-escalation.md 2.2 KB
- references/org-setup-for-adl.md 24 KB
- references/patterns-by-requirement.md 5.1 KB
- references/posture-and-determinism.md 5.0 KB
- references/production-gotchas.md 13 KB
- references/reference-map.md 4.1 KB
- references/safety-review-reference.md 6.3 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.
- 9d ago First seen · 649 lines · 186 tokens per session scan A c4aed04ca17a
agentforce-generate is a skill published in the GitHub repository SalesforceAIResearch/agentforce-adlc (105 stars, last pushed 1mo ago), with no licence file. It adds 186 tokens to every session and 14,072 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ghostswap-partners-api
Integrate the GhostSwap Partners API to add no-KYC crypto swaps (1,600+ coins, 0–4% partner fee on top of the swap, USDT payouts) into wallets, dApps, exchanges, payment flows, or affiliate sites. Use whenever a developer asks to "add crypto swap", "embed a swap widget", "let users exchange tokens", "convert crypto to…
better-tropes
Strip the tells that mark prose as AI-generated. Use when writing or editing anything a person will read: posts, articles, documentation, emails, marketing copy.
lucid-ui
Professional UI design system that replaces generic AI aesthetics (purple gradients, neon colors) with intentional, distinctive design. Use this skill whenever generating frontend UI, web pages, landing pages, dashboards, or any visual interface. Provides concrete color palettes, typography rules, spacing systems, and…
uix-components
UIX component library and protocol adapter skill for building AI chat interfaces. Use this skill when building AI agent UIs, chat interfaces, or integrating with AI protocols (Vercel AI SDK, AG-UI, Anthropic). Provides AgentChat component API, adapter usage patterns, and UIX IR (Intermediate Representation) type…
ai-form-builder
Turn a text description, screenshot, PDF, or HTML of a form into a production-ready FormEngine JSON schema plus runnable React code. Use this skill whenever the user asks to build, generate, scaffold, or convert a React form — especially when they mention FormEngine, a JSON schema form, a…
project-coding-companion
ALWAYS invoke this skill before starting ANY coding task. This skill evaluates the user's coding prompt for completeness, coaches them to clarify vague requests before any code is written, then guides implementation through a structured workflow. You MUST consult this skill whenever the user mentions code, a…