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/iblai/api/iblai-api-applynpx skills add iblai/api --skill iblai-api-applygit clone --depth 1 https://github.com/iblai/apiWhat 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 | $0.00119 | $0.11980 |
| Opus 5 | $0.00060 | $0.05990 |
| Sonnet 5 | $0.00024 | $0.02396 |
| Haiku 4.5 | $0.00012 | $0.01198 |
Grade A, and why
iblai-api-apply 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 -G \ How it starts
The opening of the file, as written. The whole thing — 879 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iblai-api-apply
Operate an organization's application gate: when applications are on, a user cannot join the org directly — they fill out a form the org configured, submit it, and staff review and decide it. Approval grants membership. Covers the applicant surface (create/renew a draft, save answers, upload files, pay or waive the fee, submit, withdraw), the reviewer surface (pipeline, per-student decisions, notes, waivers, fee management, blocks, placement tests, course assignments, account provisioning), and form management (schema, config, decision templates, renewal windows).
Applications support the family shape: one adult applies on behalf of one or more students. Each student in the application gets an individual record (a candidate) with its own review status and decision — one child can be accepted while a sibling is waitlisted. A form with no student section is a plain self-apply form; the applicant is the candidate. A user's application record is called a submission in the API payloads; the two words refer to the same thing.
Three kinds of caller hit these endpoints:
- Applicant — a signed-in user. Creates and submits an application (for themselves or their students), watches its status, pays or has waived the application fee, and can renew next year.
- Reviewer / admin — an org admin. Works the pipeline, decides per student or per family, keeps internal notes, manages the fee, waives requirements, assigns placement tests and courses after acceptance.
- Form manager — an org admin. Authors the form(s), the decision message templates, the fee, and the renewal window.
Auth & conventions
- Base URL:
https://api.iblai.app/dm— these are Data Manager (DM) endpoints, so the/dmprefix is required; the/api/catalog/applications/...paths below are appended to it (e.g.https://api.iblai.app/dm/api/catalog/applications/platform/status). (The same contract is also exposed edX-proxied under/api/ibl/catalog/applications/...; through this gateway use the direct/dmform.) Trailing slashes are accepted but optional on every route. - Header:
Authorization: Api-Token $IBLAI_API_KEYon every request. - Org scope: every request is scoped to one org. Pass
platform_key(=$IBLAI_ORG) as a query param on GETs and in the body on writes;platform_org(the org code) is accepted as an alternative. Reviewer endpoints that address a specific application by id resolve the org from the application itself, but list/stats/detail reads still takeplatform_keyfor the permission check. - Authentication semantics: all endpoints require authentication;
anonymous requests get
401. Reviewer and form-manager endpoints (managepaths) additionally enforce admin/role permissions and return403when the caller lacks them. Applicant endpoints operate only on the caller's own applications — someone else's application id is a404, not a403(no existence leak). - Pagination: only the reviewer pipeline list is paginated, with the
standard envelope
{ "count", "next", "previous", "results": [...] }andpage/page_sizeparams. Every other list returns a plain{ "results": [...] }with no paging. - Errors: business errors return a stable machine code:
{ "error": "<machine_code>" }— key offerror. Validation failures on submit are richer (see Answers and validation errors below). Throttled writes return429. - Timestamps are ISO 8601. Money is a decimal string (
"50.00") plus acurrencycode. <id>in paths is a submission id unless stated otherwise.- DELETE / destructive / outward-facing calls say "Confirm with the user first."
- Not connected yet? Run
/iblai-api-loginfirst to populateIBLAI_ORG,IBLAI_USERNAME, andIBLAI_API_KEY.
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.
- 3d ago First seen · 879 lines · 119 tokens per session scan A 27cf52eab6ba
iblai-api-apply is a skill published in the GitHub repository iblai/api (15 stars, last pushed 4d ago), licensed MIT. It adds 119 tokens to every session and 11,980 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.
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…
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…
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…
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.
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.
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.