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 agentmods add skills/pipefy/ai-toolkit/pipefy-api-fallbacknpx skills add pipefy/ai-toolkit --skill pipefy-api-fallbackgit clone --depth 1 https://github.com/pipefy/ai-toolkitWhat 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 | $0.00086 | $0.02675 |
| Opus 5 | $0.00043 | $0.01337 |
| Sonnet 5 | $0.00017 | $0.00535 |
| Haiku 4.5 | $0.00009 | $0.00267 |
Grade A, and why
pipefy-api-fallback scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
call the Pipefy GraphQL API directly using curl or httpx, authenticating How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipefy API Fallback (Tier 3 — Last Resort)
This skill activates only after Tiers 1 and 2 have failed. Call the Pipefy GraphQL API directly, bypassing the MCP server.
3-tier resolution strategy (always follow in order)
| Tier | Method | When |
|---|---|---|
| 1 | Dedicated MCP tool (create_card, get_phase_cards, get_phase_allowed_move_targets, update_pipe, etc.) |
Always try first. For card/phase seeding and inventory, see Seed pipe across phases. |
| 2 | Introspection + execute_graphql |
When no dedicated tool exists or a tool fails unexpectedly. See skills/introspection/pipefy-introspection/SKILL.md. |
| 3 | Direct HTTP via curl / httpx (this skill) | When the MCP server itself is unavailable, or execute_graphql fails with an infrastructure error. |
Do not jump to Tier 3 after a single tool failure. Follow the tiers in order.
Authentication
Two options (use whichever is available in the environment). Prefer the Service Account when both exist.
Option A — OAuth2 Client Credentials (preferred):
TOKEN=$(curl -s -X POST https://app.pipefy.com/oauth/token \
-H "Content-Type: application/json" \
-d "{\"grant_type\":\"client_credentials\",\"client_id\":\"$PIPEFY_SERVICE_ACCOUNT_CLIENT_ID\",\"client_secret\":\"$PIPEFY_SERVICE_ACCOUNT_CLIENT_SECRET\"}" \
| python3 -c "import sys,json; print(json.load(sys.stdin)['access_token'])")
Option B — Personal Access Token (PAT):
TOKEN="$PIPEFY_PAT" # or $PIPEFY_TOKEN
PATs are deprecated for new integrations but may still exist in the environment.
Token rules
- The
Bearerprefix is mandatory — Pipefy rejects requests without it. - Never expose
PIPEFY_SERVICE_ACCOUNT_CLIENT_ID,PIPEFY_SERVICE_ACCOUNT_CLIENT_SECRET,PIPEFY_PAT, orPIPEFY_TOKENin responses to the user or in logs. - Service Account tokens are reused while valid; only re-fetch on expiry (401).
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 First seen · 230 lines · 86 tokens per session scan A 58b3254225c2
pipefy-api-fallback is a skill published in the GitHub repository pipefy/ai-toolkit (44 stars, last pushed 6d ago), licensed Apache-2.0. It adds 86 tokens to every session and 2,675 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 2026-08-30.
Other skills, from other repositories
create-tutorial
Scaffold a new Membrane API Gateway tutorial in the api-gateway repo — the numbered self-teaching YAML under distribution/tutorials/ /, its support files and README links, and the matching auto-discovered integration test. Use whenever the user asks to create, add, write, or scaffold a tutorial (or a tutorial step)…
optimize-interceptor-docs
Rewrite the reference documentation of a Membrane config element so the page generated at membrane-api.io comes out clean, exact, and reference-style. Use whenever the user wants to write, improve, optimize, polish, or review the docs / Javadoc / @description / @yaml example of an interceptor, plugin, or any…
release-notes
Generate GitHub release notes for the Membrane api-gateway repo by collecting the commits between the last release and master, grouping them into Features / Improvements / Fixes / Security / Dependencies, and linking each to its PR. Use whenever the user wants to draft, extract, or write release notes / a changelog /…
find-interceptor-impl
Find the Java implementation class behind a Membrane interceptor or config element given its XML name (the @MCElement value), e.g. "which class implements the interceptor?". Use whenever the user references an interceptor / plugin / config element by its proxies.xml tag name (groovy, apiKey, rewriter, log, ...) and…
lap
LAP CLI -- compile, search, and manage API specs for AI agents. Use when working with API specifications (OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman), compiling specs to LAP format, searching the LAP registry, generating skills from API specs, or publishing APIs. Commands: init, compile, search, get, skill…
aade-api-monitor
Real-time monitoring of Greek AADE tax authority systems — tracks deadlines, rate changes, and compliance updates. File-based, OpenClaw-native.