iblai-api-feature

A tool for managing per-user and platform feature settings through the ibl.ai Data Manager API. It also handles app access, onboarding status, free trials, and supported platform provisioning.

In plain words
What is it for?
Use it to read or change a user's feature configuration, apply a feature value across users, list accessible apps, complete onboarding, grant a trial, or provision a platform when enabled.
Why use it?
It removes the need to construct these administrative API requests manually and documents the required gateway URL, authentication, and organization values. This helps avoid sending configuration to the wrong platform or endpoint.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/iblai/api/iblai-api-feature
Any agent
npx skills add iblai/api --skill iblai-api-feature
Clone the repo
git clone --depth 1 https://github.com/iblai/api

Made for: Claude Code, Codex.

Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,603 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00124 $0.02603
Opus 5 $0.00062 $0.01301
Sonnet 5 $0.00025 $0.00521
Haiku 4.5 $0.00012 $0.00260

Measured 3d ago against content hash 7aef0c712dd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

iblai-api-feature 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 3d 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.

curl -X POST \
skills/iblai-api-feature/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

iblai-api-feature

Manage per-user feature configuration and app / onboarding state from the Data Manager (DM) API: read and write a user's feature config (one feature, or a bulk inline config object), bulk-apply a feature's values across every user on a platform, list the apps a user has access to, mark onboarding complete, activate an app free trial, and — only when the platform enables it — run an admin platform-provisioning config. Use when flipping feature flags/values for a user or an org, inspecting a user's apps, recording onboarding, granting a trial, or provisioning a platform.

Auth & conventions

  • Base URL: https://api.iblai.app/dm — these are Data Manager (DM) endpoints, so the /dm prefix is required; the /api/features/... (and /api/provision/...) paths below are appended to it (e.g. https://api.iblai.app/dm/api/features/config/). /dm is the gateway prefix and does not appear in the app's urls.py.
  • Header: Authorization: Api-Token $IBLAI_API_KEY on every request.
  • Path / scope vars: {org} = $IBLAI_ORG (a.k.a. platform_key on the wire). The org/platform is always passed as a query param or body field (platform_key), never baked into the path. The user is resolved flexibly from user_id or username or email (in that precedence) — passed as query params on GET, body fields on POST.
  • Most feature/app endpoints are open (AllowAny — see Notes); the provisioning endpoint is platform-admin only. Destructive / outward-facing actions (trial activation) say "Confirm with the user first."
  • Not connected yet? Run /iblai-api-login first to populate IBLAI_ORG, IBLAI_USERNAME, and IBLAI_API_KEY.

Reads

Feature config

A user's feature config is a set of per-platform {feature: values} records. Reads return the whole map; writes accept either a bulk inline config object or a single feature + values pair (these two body shapes are mutually exclusive — config wins if both are present, otherwise feature is used; sending neither returns 400).

Read the full file on GitHub · 206 lines

Changes

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.

  1. 3d ago First seen · 206 lines · 124 tokens per session scan A 7aef0c712dd8

Subscribe to this mod's changes

iblai-api-feature is a skill published in the GitHub repository iblai/api (15 stars, last pushed 4d ago), licensed MIT. It adds 124 tokens to every session and 2,603 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

vindicate

Use when the user wants to write, add, fix, stabilize (flaky), refactor, run, or audit Playwright browser tests, draft requirements/stories from a recording (no tests), find test-coverage gaps, scaffold a Playwright project, or set up Playwright CI. Vindicate's guided workflow for grounded, conformant Playwright test…

OpenEvident/vindicate · 77 tokens

audit

Audits recent work against its Definition of Done and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. Generates an incremental prompt pack for any gaps found. With…

pe-menezes/vibeflow · 93 tokens

implement

Implements a feature from its spec following all guardrails: budget, DoD, anti-scope, and pattern compliance. Runs an 8-phase pipeline (find spec → extract guardrails → load patterns → plan → implement → test → refine → self-verify DoD). Use after gen-spec when you're ready to code. The agent has filesystem access and…

pe-menezes/vibeflow · 79 tokens

assistant

Assistant — on any repo, scan README→docs→AGENTS→CONTRIBUTING→PR templates→task runners→devcontainer→CI→configs before code; cite sources; prefer AGENTS.md for agent behavior; portable across Cursor/Copilot/Claude; use agent-toolkit CLI when needed.

ulises-jeremias/agent-toolkit · 64 tokens

design-improvement

WHAT - Browser-grounded iterative design improvement. Consumes design-assessment findings, defines direction, prioritizes safe vs ambiguous changes, implements within existing design system, runs app, captures rendered evidence via browser, reviews and iterates. Reuses evidence model — no new scoring framework.

ulises-jeremias/agent-toolkit · 60 tokens

codeql

CodeQL operational workflow — discover/config, run/inspect, triage SARIF findings (rule/query ID, source→sink, evidence), remediate, re-validate. Distinguishes broad MegaLinter linting from semantic security analysis.

ulises-jeremias/agent-toolkit · 52 tokens