Borrowing it
Nothing to install: this file belongs to ElioLin/sfoa-enterprise-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ElioLin/sfoa-enterprise-mcp/main/.agents/skills/sfoa-mcp-maintainer/SKILL.mdgit clone --depth 1 https://github.com/ElioLin/sfoa-enterprise-mcpWrote 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/eliolin/sfoa-enterprise-mcp/sfoa-mcp-maintainer)<a href="https://agentmods.dev/skills/eliolin/sfoa-enterprise-mcp/sfoa-mcp-maintainer"><img src="https://agentmods.dev/badge/skills/eliolin/sfoa-enterprise-mcp/sfoa-mcp-maintainer/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/eliolin/sfoa-enterprise-mcp/sfoa-mcp-maintainer"><img src="https://agentmods.dev/badge/skills/eliolin/sfoa-enterprise-mcp/sfoa-mcp-maintainer.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 | $0.00070 | $0.01285 |
| Opus 5 | $0.00035 | $0.00642 |
| Sonnet 5 | $0.00014 | $0.00257 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
sfoa-mcp-maintainer 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SFoA MCP Maintainer
Use this Skill for engineering and operations work in sfoa-enterprise-mcp. It is advisory project context, not a reasoning boundary. Use other tools and approaches when they improve the investigation.
Current source code, runtime behavior, MySQL state, logs, P7 Audit evidence, Salesforce API responses, and tests outrank this Skill. When they conflict, investigate the difference, report verified facts, and update the Skill only if durable project knowledge changed.
Start with evidence
- Read the repository
AGENTS.mdand the relevant current baseline/architecture files it names. - Run
yarn ai:snapshotto verify packages, scripts, migrations, and catalog sources from the checkout. - Run
yarn ai:doctorwhen local runtime, database, Admin, or environment state matters. - Read only the references needed for the task below; inspect current code before deciding.
- Preserve the accepted request-scoped identity, Salesforce authorization, Tool-governance, DML, and Audit fail-open boundaries unless the task intentionally changes them.
Never print or paste .env.local. The diagnostic scripts load it locally and report configured/missing state without returning secret values.
Route by task
- Architecture or takeover: read architecture.md, repository-map.md, and runtime-flow.md.
- MySQL, identity, governance, or P7 evidence: read database-audit.md. Use
yarn ai:db --report <name>andyarn ai:auditbefore ad hoc SQL. - Incident or bug investigation: read troubleshooting.md and follow the evidence chain rather than assuming one layer caused the symptom.
- TypeScript/React/MCP implementation or review: read development.md and the nearest package
README.md/DEVELOPING.md. - Startup, health, deployment, and maintenance: read operations.md.
- Gate selection and verification: read testing.md.
- Effective CREATE / Dynamic Forms / UI snapshots: read p8-04-effective-create.md.
- Batch DML / display labels / compound intent / CREATE initial facts: read p8-07-runtime-batch.md.
- Skill or durable project-fact changes: read skill-maintenance.md.
- The “Lead only; Account/Opportunity unavailable” validation case: read acceptance-scenario.md.
What ships with it
22 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.
- agents/openai.yaml 292 B
- references/acceptance-scenario.md 2.2 KB
- references/architecture.md 6.4 KB
- references/database-audit.md 4.2 KB
- references/development.md 2.2 KB
- references/operations.md 2.1 KB
- references/p8-04-effective-create.md 9.9 KB
- references/p8-07-runtime-batch.md 8.5 KB
- references/repository-map.md 2.7 KB
- references/runtime-flow.md 5.5 KB
- references/skill-maintenance.md 1.9 KB
- references/testing.md 3.2 KB
- references/troubleshooting.md 2.9 KB
- scripts/audit-trace.mjs 20 KB runs code
- scripts/clean-checkout-smoke.mjs 7.6 KB runs code
- scripts/db-inspect.mjs 10 KB runs code
- scripts/doctor.mjs 9.7 KB runs code
- scripts/manage.mjs 15 KB runs code
- scripts/project-snapshot.mjs 6.2 KB runs code
- scripts/shared/db.mjs 4.4 KB runs code
- scripts/shared/project.mjs 7.8 KB runs code
- scripts/toolkit.test.mjs 12 KB runs code
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 Changed · +1 lines 1581484a32e9
- 4d ago Changed · +2 lines 406fc304a85c
- 8d ago First seen · 63 lines · 70 tokens per session scan A cf34442e3c39
sfoa-mcp-maintainer is a skill published in the GitHub repository ElioLin/sfoa-enterprise-mcp (0 stars, last pushed today), licensed Apache-2.0. It adds 70 tokens to every session and 1,285 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
convex-explain-app
Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.
platform-custom-field-generate
Use this skill when users need to create, generate, or validate Salesforce Custom Field metadata. Trigger when users mention custom fields, field types, Roll-up Summary fields, Master-Detail relationships, Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from…
field-service-sobject-create-configure
Headless 360 REST API deployment step for creating sObject records. Handles describe-based field discovery, required-field derivation, entity-relationship ordering, and composite graph transactions. Use this skill when a designer skill (or a user directly) needs to create sObject records after design confirmation…
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
nornicdb-grpc
Drive NornicDB over gRPC — the Qdrant-compatible surface (Collections, Points, Snapshots) plus the additive NornicSearch service. Use when ingesting via Qdrant SDKs, migrating from Qdrant, or running hybrid text+vector search from a non-Bolt client. Covers connection, RPC catalog, collection→database mapping…