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 forcedotcom/sf-skills --skill platform-manifest-generategit clone --depth 1 https://github.com/forcedotcom/sf-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/forcedotcom/sf-skills/platform-manifest-generate)<a href="https://agentmods.dev/skills/forcedotcom/sf-skills/platform-manifest-generate"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/platform-manifest-generate/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/forcedotcom/sf-skills/platform-manifest-generate"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/platform-manifest-generate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00176 | $0.03355 |
| Opus 5 | $0.00088 | $0.01677 |
| Sonnet 5 | $0.00035 | $0.00671 |
| Haiku 4.5 | $0.00018 | $0.00335 |
Grade A, and why
platform-manifest-generate 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.
How it starts
The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
platform-manifest-generate
Produce a Salesforce metadata manifest — package.xml (or one of the destructive variants) — from local source, an org, or an explicit component list. This skill is purely about authoring the manifest file. Hand off to platform-metadata-deploy or platform-destructive-deploy once the file exists.
Tool Restrictions
Use ONLY the Bash tool to run sf project generate manifest, and the Write tool for the hand-built fallback path. Do NOT use MCP tools.
When This Skill Owns the Task
Use platform-manifest-generate when the work involves any of:
- Building a
package.xmlfrom a source directory (e.g.force-app/main/default/classes/) - Building a manifest from an explicit list of components (e.g.
AccountService,ContactSelector,Account) - Building a manifest by introspecting an org via
--from-org - Producing
destructiveChanges.xml,destructiveChangesPre.xml, ordestructiveChangesPost.xmlfor a deletion - Producing both a
package.xmland a destructive manifest in one operation
Delegate elsewhere when the user is:
- Running the deploy itself →
platform-metadata-deploy - Validating before a prod release →
platform-deploy-validate - Executing the destructive deploy →
platform-destructive-deploy(that skill uses the manifest this skill generates) - Retrieving metadata to local →
platform-metadata-retrieve
Two Generation Paths
Path A — CLI-driven (recommended)
Wrap sf project generate manifest. Always prefer this path; it knows about every metadata type and produces canonical XML — and never emits *, sidestepping the wildcard hazard entirely.
The CLI offers three input modes (mutually exclusive):
| Input | Flag | Use when |
|---|---|---|
| Source directory | --source-dir (-p) |
User points to a folder containing already-on-disk metadata |
| Component list | --metadata (-m) |
User names specific components, e.g. ApexClass:AccountService CustomObject:Account |
| Org introspection | --from-org |
User wants every component currently in an org (or a filtered subset) |
What ships with it
1 file 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.
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 First seen · 309 lines · 176 tokens per session scan A 7202de83d495
platform-manifest-generate is a skill published in the GitHub repository forcedotcom/sf-skills (987 stars, last pushed today), licensed Apache-2.0. It adds 176 tokens to every session and 3,355 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…