Borrowing it
Nothing to install: this file belongs to Othmane-Khadri/YALC-the-GTM-operating-system. 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/Othmane-Khadri/YALC-the-GTM-operating-system/main/.claude/skills/provider-builder/SKILL.mdgit clone --depth 1 https://github.com/Othmane-Khadri/YALC-the-GTM-operating-systemWrote 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/othmane-khadri/yalc-the-gtm-operating-system/provider-builder)<a href="https://agentmods.dev/skills/othmane-khadri/yalc-the-gtm-operating-system/provider-builder"><img src="https://agentmods.dev/badge/skills/othmane-khadri/yalc-the-gtm-operating-system/provider-builder/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/othmane-khadri/yalc-the-gtm-operating-system/provider-builder"><img src="https://agentmods.dev/badge/skills/othmane-khadri/yalc-the-gtm-operating-system/provider-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 75 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Data Exfiltration · line 94 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Rogue Agent · line 153 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00124 | $0.03361 |
| Opus 5 | $0.00062 | $0.01681 |
| Sonnet 5 | $0.00025 | $0.00672 |
| Haiku 4.5 | $0.00012 | $0.00336 |
Grade A, and why
provider-builder 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.
If the docs page lacks a response example, an error envelope, or an auth section, ask the user for that one piece. Never invent fields. If the user can't supply it (e.g., docs are private), suggest they run a real call w How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Provider Builder
Author a declarative adapter manifest from a vendor name, a capability id, and a docs URL. Drafts YAML, smoke-tests against the live vendor, and only then registers the file under ~/.gtm-os/adapters/. Built on the manifest schema in src/lib/providers/declarative/types.ts and the adapters:smoke runner. Never writes secrets into the manifest, never prints API keys back to the user, never reads ~/.gtm-os/.env.
When to use
- "Add Apollo as a second provider for
icp-company-search" - "Wire up PeopleDataLabs for
people-enrich" - "Try Brevo instead of Instantly for
email-campaign-create" - Hot-patching a broken built-in by dropping a YAML with the same provider id
Don't use when: the vendor needs OAuth, request signing (Sigv4 / HMAC), gRPC / websockets, an SDK-only client, or two-call flows (/token then /search). All of those are out of scope for declarative v1 — exit with a stub TS template (see Failure mode 2 below).
Pre-flight (do this before step 1)
-
Onboarding interruption guard. Run:
test -f ~/.gtm-os/.in-flight-setup && echo "BLOCKED" || echo "OK"If
BLOCKED, stop. Tell the user: "Setup is mid-flight. Finishyalc-gtm startfirst, then re-invoke me." Exit cleanly. This skill writes to the adapter registry from Step 5 onward, so it must not race the onboarding flow. -
Confirm the trigger is in scope. If the user mentioned OAuth, an SDK, gRPC, or signed requests, jump to Failure mode 2 and exit cleanly.
-
Confirm
pnpm cli adapters:listworks in the cwd. If not, the package isn't built or the user is in the wrong directory — surface that and stop. -
Resolve the env var name with the user (e.g.,
APOLLO_API_KEY). Do not open~/.gtm-os/.env. Useprocess.envonly —node -e "console.log(process.env.APOLLO_API_KEY ? 'set' : 'unset')"is the maximum disclosure allowed (printsset/unset, never the value).
Workflow
Step 0 — Greet + state scope
What ships with it
2 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.
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 · 244 lines · 124 tokens per session scan A 06798002b921
provider-builder is a skill published in the GitHub repository Othmane-Khadri/YALC-the-GTM-operating-system (301 stars, last pushed 22d ago), licensed MIT. It adds 124 tokens to every session and 3,361 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
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
kn-handoff
Use when a feature crosses repository boundaries and one side must hand work to the other - generates a self-contained frontend-to-backend brief or backend-to-frontend API contract.
kn-spec
Use when creating a specification document for a feature (SDD workflow).
kn-flow
Use when orchestrating a full Knowns spec or task wave through planning, implementation, review, integration, and verification, optionally using sub-agents when scopes are parallel-safe.
kn-debug
Use when debugging errors, test failures, build issues, or blocked tasks — structured triage to fix to learn.
kn-research
Use when you need to understand existing code, find patterns, search project knowledge, investigate current external facts, or explore a large codebase before implementation.