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 khalilbenaz/claude-skills-collection --skill api-caller-subagentgit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/khalilbenaz/claude-skills-collection/api-caller-subagent)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/api-caller-subagent"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/api-caller-subagent/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/khalilbenaz/claude-skills-collection/api-caller-subagent"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/api-caller-subagent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Data Exfiltration · line 333 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 Data Exfiltration · line 336 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.
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 | $0.00088 | $0.03094 |
| Opus 5 | $0.00044 | $0.01547 |
| Sonnet 5 | $0.00018 | $0.00619 |
| Haiku 4.5 | $0.00009 | $0.00309 |
Grade A, and why
api-caller-subagent 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 11d 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.
from urllib.parse import urlparse How it starts
The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Caller Sub-Agent
Quand utiliser ce skill
Déléguer à ce sous-agent tout appel réseau sortant depuis un agent parent : intégration d'APIs tierces, scraping structuré via API, agrégation multi-sources, synchronisation de données.
Critères de décision :
- Plusieurs APIs différentes dans le même workflow → sous-agent par API ou sous-agent unique réutilisé
- Auth complexe (OAuth2, rotation de token) → toujours isoler dans ce sous-agent
- Pagination ou rate limiting → laisser le sous-agent gérer, l'agent parent ne voit qu'un tableau plat
- Requête unique simple GET sans auth → acceptable en direct si le contexte est simple
Workflow en 10 étapes
1. Validation des inputs
Avant toute connexion réseau, valider :
from urllib.parse import urlparse
def validate_input(inp: dict) -> None:
parsed = urlparse(inp["url"])
assert parsed.scheme in ("https", "http"), "Schéma invalide"
assert parsed.netloc, "URL sans hôte"
assert inp["method"].upper() in (
"GET","POST","PUT","PATCH","DELETE","HEAD","GRAPHQL"
), f"Méthode inconnue: {inp['method']}"
if inp.get("auth", {}).get("type") not in (
None,"none","api_key","bearer","oauth2","jwt","basic"
):
raise ValueError("auth.type non supporté")
Retourner immédiatement un output d'erreur formaté sans lever d'exception non catchée.
2. Résolution de l'authentification
Choisir le handler selon auth.type :
| Type | Implémentation |
|---|---|
api_key |
Header X-Api-Key ou query param ?api_key= |
bearer |
Authorization: Bearer {token} |
basic |
Authorization: Basic {b64(user:pass)} |
oauth2 |
Client Credentials : POST /token, stocker + rafraîchir |
jwt |
PyJWT.encode(payload, secret, algorithm="HS256") |
import base64, httpx, jwt, time
def build_auth_headers(auth: dict) -> dict:
t = auth.get("type", "none")
c = auth.get("credentials", {})
if t == "bearer":
return {"Authorization": f"Bearer {c['token']}"}
if t == "basic":
raw = base64.b64encode(f"{c['username']}:{c['password']}".encode()).decode()
return {"Authorization": f"Basic {raw}"}
if t == "api_key":
return {c.get("header_name", "X-Api-Key"): c["key"]}
if t == "jwt":
token = jwt.encode(
{"sub": c.get("sub","agent"), "exp": int(time.time()) + 3600},
c["secret"], algorithm="HS256"
)
return {"Authorization": f"Bearer {token}"}
return {}
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.
- 11d ago First seen · 345 lines · 88 tokens per session scan A fc207e367e61
api-caller-subagent is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 17d ago), licensed MIT. It adds 88 tokens to every session and 3,094 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
csharp-patterns
C#/.NET: LINQ, async/await, DI, records, nullable refs, ASP.NET Core, EF Core, MediatR. Triggers: C#, .NET, dotnet, ASP.NET, EF Core, LINQ, record type, IServiceCollection.
api-patterns
API design: naming, versioning, pagination, idempotency, OpenAPI, error contracts and safe retries. Triggers: API design, REST, GraphQL, OpenAPI, Swagger, error response, HTTP status, rate limit.
java-patterns
Java: Spring Boot, CompletableFuture, records, sealed types, JPA/Hibernate, virtual threads. Triggers: Java, Spring, JPA, Hibernate, Maven, Gradle, virtual thread, sealed class.
explain
Explains code/architecture with Mermaid diagrams and sequence flows. Triggers: what does X do, how does Y work, explain code, sequence diagram.
common-sense-index-investing-bogle
Apply John Bogle index investing rules for low-cost funds, asset allocation, fees, taxes, ETFs, advisers, and buy-hold discipline.
medplum-rules
Medplum (FHIR healthcare) coding rules: style, patterns, security, testing. Triggers: medplum.config.mts, medplum.config.ts, FHIR, Medplum, Bot, Subscription, Questionnaire.