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 orkestre-ai/orkestre-engaging-networks --skill engaging-networks-apigit clone --depth 1 https://github.com/orkestre-ai/orkestre-engaging-networksWrote 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/orkestre-ai/orkestre-engaging-networks/engaging-networks-api)<a href="https://agentmods.dev/skills/orkestre-ai/orkestre-engaging-networks/engaging-networks-api"><img src="https://agentmods.dev/badge/skills/orkestre-ai/orkestre-engaging-networks/engaging-networks-api/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/orkestre-ai/orkestre-engaging-networks/engaging-networks-api"><img src="https://agentmods.dev/badge/skills/orkestre-ai/orkestre-engaging-networks/engaging-networks-api.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 | $0.00085 | $0.02800 |
| Opus 5 | $0.00043 | $0.01400 |
| Sonnet 5 | $0.00017 | $0.00560 |
| Haiku 4.5 | $0.00009 | $0.00280 |
Grade A, and why
engaging-networks-api scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
SESSION_TOKEN=$(curl -s -X POST \ How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<essential_principles>
<authentication_overview> The Engaging Networks REST API provides programmatic access to fundraising pages, supporter data, and campaign metrics for nonprofit organizations.
Session-based authentication (two-step process):
- Obtain API User token from EN admin (Settings -> API Users)
- POST to /authenticate with API User token to get session token
- Use session token in
ens-auth-tokenheader for all subsequent requests - Session tokens expire (typically 1 hour) - re-authenticate when expired
- Store API User token securely in environment variables
- Never expose tokens in client-side code or logs
- Ensure IP addresses are whitelisted in API User settings
Two token types:
- API User Token: Permanent UUID from EN Admin, used ONLY for POST /authenticate
- Session Token: Temporary token from /authenticate response, used for all other API calls </authentication_overview>
<rate_limits_overview> Hard limits:
- 5,000 requests per hour per API user (EN-specific)
- 200 page processing requests per 5 minutes per IP
- HTTP 429 response when exceeded
Best practices:
- Implement exponential backoff with jitter
- Cache page metadata (changes infrequently)
- Use maximum pagination limit (100)
- Schedule data collection during off-peak hours </rate_limits_overview>
<regional_instances> EN has multiple deployments - use the correct one:
- US:
https://us.engagingnetworks.app/ens/service - US2:
https://us2.engagingnetworks.app/ens/service - CA:
https://ca.engagingnetworks.app/ens/service
Note: EU and AU clients currently use the CA servers (ca.engagingnetworks.app). There are no separate eu. or au. endpoints at this time. If your organization was provisioned under an EU or AU label, use the CA base URL.
Check your EN admin panel URL to determine your region. </regional_instances>
<data_model> Core entities:
- Pages: Campaign pages (donation, advocacy, event, survey) with configuration
- Page Components: Reusable building blocks (code blocks, form blocks, templates, text blocks, thank-you emails, upsell lightboxes, display widgets)
- Supporters: Contact records with fields, questions, memberships, and suppression status
- Transactions: Donation/payment records accessed via supporter (NOT via page)
- Recurring Transactions: Recurring payment schedules per supporter
- Origin Sources: Acquisition channel tracking per supporter
- Export Jobs: Asynchronous bulk data exports from pre-configured queries
- Marketing Automations: Automated supporter journeys with stats
- Account: Audit log access
Typical integration flow:
- Authenticate (POST /authenticate) to get session token
- List pages by type (GET /page?type=dc&status=live)
- Look up supporters (GET /supporter?email=... or GET /supporter/query)
- Access supporter transactions (GET /supporter/{id}/transactions)
- Manage origin sources (GET/POST/PUT/DELETE /supporter/{id}/originsource)
- Run export jobs for bulk data (POST /exportjob, poll, download)
- Process page submissions (POST /page/{id}/process) </data_model>
<error_handling_overview> Retry on:
- 429 (rate limit) - with exponential backoff
- 5xx (server errors) - with fixed delay
Don't retry:
- 400 (bad request) - fix the request
- 401 (unauthorized) - check token
- 403 (forbidden) - check permissions
- 404 (not found) - resource doesn't exist </error_handling_overview>
<data_privacy> This skill is a development assistant. Its primary purpose is helping you write, debug, and deploy code that uses the EN API — not acting as a live data operations proxy.
Recommended: use a sandbox or test EN account. All workflows work without real donor data.
Data flow awareness: When the agent executes EN API calls, response data is processed by the model provider's infrastructure (Anthropic, OpenAI, etc.). Any supporter PII in API responses — names, emails, addresses, donation history — is transferred to a third party during inference. Read operations expose PII even though they don't modify data.
What ships with it
13 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.
- README.md 14 KB
- references/authentication.md 19 KB
- references/common-patterns.md 28 KB
- references/endpoints.md 39 KB
- references/error-handling.md 9.9 KB
- references/rate-limits.md 9.3 KB
- references/typescript-client.md 30 KB
- workflows/add-endpoint.md 12 KB
- workflows/build-integration.md 20 KB
- workflows/debug-api-issues.md 10 KB
- workflows/deploy-integration.md 11 KB
- workflows/optimize-api-usage.md 13 KB
- workflows/test-integration.md 15 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.
- 12d ago First seen · 239 lines · 85 tokens per session scan A cccd7522e21d
engaging-networks-api is a skill published in the GitHub repository orkestre-ai/orkestre-engaging-networks (4 stars, last pushed 5mo ago), licensed MIT. It adds 85 tokens to every session and 2,800 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
ubiquitous-language
Maintain a project thesaurus (domain glossary) following DDD ubiquitous language principles. Use PROACTIVELY when naming anything: variables, functions, classes, modules, database fields, API endpoints, events, files, or directories. Also use when the user asks to "create thesaurus", "update glossary", "add term"…
neo4j-getting-started-skill
Orchestrates zero-to-running-app in 8 stages — prerequisites → context → provision → model → load → explore → query → build. Each stage reads its own reference file. Supports HITL and fully autonomous operation. Use when starting a new Neo4j project from scratch, provisioning Aura, generating synthetic data, building…
neo4j-graphql-skill
Build and configure a GraphQL API backed by Neo4j using @neo4j/graphql v7 (current) or v5 (LTS). Covers Neo4jGraphQL constructor, getSchema(), assertIndexesAndConstraints(), type definitions with @node, @relationship (IN/OUT/UNDIRECTED), @cypher for custom resolvers, @authorization/@authentication for JWT/JWKS…
neo4j-kafka-skill
Configure and operate the Neo4j Connector for Kafka (sink + source) and the native Neo4j CDC API. Covers Cypher/Pattern/CUD sink strategies, CDC-based and query-based source, exactly-once semantics, DLQ error handling, Confluent Cloud managed connector, schema registry (Avro/JSON), and native db.cdc.query cursor-loop…
kirby-routing-and-representations
Implements custom Kirby routes and content representations (.json/.xml/.rss), including redirects, sitemap endpoints, and URL pattern filtering. Use when building endpoints, redirects, or representation templates that change how URLs resolve.
kirby-scaffold-page-type
Scaffolds a new Kirby page type (blueprint + template, optional controller/model) using project roots, index tools, and Panel field/section references. Use when creating a new page type or extending an existing blueprint/template.