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 mayai-it/bandiradar --skill add-a-sourcegit clone --depth 1 https://github.com/mayai-it/bandiradarWrote 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/mayai-it/bandiradar/add-a-source)<a href="https://agentmods.dev/skills/mayai-it/bandiradar/add-a-source"><img src="https://agentmods.dev/badge/skills/mayai-it/bandiradar/add-a-source/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/mayai-it/bandiradar/add-a-source"><img src="https://agentmods.dev/badge/skills/mayai-it/bandiradar/add-a-source.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00087 | $0.01584 |
| Opus 5 | $0.00044 | $0.00792 |
| Sonnet 5 | $0.00017 | $0.00317 |
| Haiku 4.5 | $0.00009 | $0.00158 |
Grade A, and why
add-a-source 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 9d 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.
def fetch(self, since: datetime | None = None) -> Iterable[RawDoc]: ... How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a Source to BandiRadar
A source is the project's one extension point (ARCHITECTURE.md §5). Adding one is a new file + a fixture + a test — no changes to core, the matcher, or storage. The long tail of regional bandi is meant to be crowdsourced this way.
The Source contract
class Source(Protocol):
id: str # unique, e.g. "regione_lazio"
kind: Literal["tender", "grant", "incentive"]
def fetch(self, since: datetime | None = None) -> Iterable[RawDoc]: ...
def to_opportunities(self, raw: RawDoc, now=None) -> list[Opportunity]: ...
fetch()pulls raw payloads (HTTP/feed/API) and yieldsRawDocs.to_opportunities()is a PURE mapping: raw → canonicalOpportunity. No network, no I/O — so it is unit-testable offline against a fixture.
Steps
1. Skeleton adapter — src/bandiradar/sources/<name>.py
"""<Name> source adapter."""
from __future__ import annotations
import json
from collections.abc import Iterable
from datetime import datetime
from pathlib import Path
from typing import Any
from bandiradar.models import Kind, Opportunity, RawDoc, default_status
from bandiradar.sources.base import register
SOURCE_ID = "<name>"
SOURCE_KIND: Kind = "grant" # or "tender" / "incentive"
# Do NOT invent a live endpoint. Leave empty + a TODO until confirmed.
SOURCE_URL = ""
FIXTURE_PATH = (
Path(__file__).resolve().parents[3] / "data" / "fixtures" / "<name>.json"
)
def to_opportunities(raw: RawDoc, now: datetime | None = None) -> list[Opportunity]:
"""PURE: map one raw record (raw.payload) into Opportunity objects."""
record: dict[str, Any] = raw.payload
deadline = None # parse from record, e.g. datetime.fromisoformat(...)
return [
Opportunity(
id=f"{SOURCE_ID}:{record['id']}",
source=SOURCE_ID,
source_url=record.get("url") or raw.url or "",
kind=SOURCE_KIND,
title=record["title"],
summary=record.get("description"),
issuer_name=record.get("issuer"),
issuer_region=record.get("region"),
cpv=record.get("cpv", []),
value_amount=record.get("amount"),
geo_scope="regional" if record.get("region") else "national",
region=record.get("region"),
deadline=deadline,
status=default_status(deadline, now),
eligibility_text=record.get("eligibility"),
raw_ref=raw.id,
# content_hash auto-fills — do not set it.
)
]
def load_fixture(path: Path | None = None) -> list[RawDoc]:
"""Recorded payloads -> RawDocs, for offline use and tests."""
data = json.loads((path or FIXTURE_PATH).read_text(encoding="utf-8"))
fetched_at = datetime.fromisoformat("1970-01-01T00:00:00+00:00")
return [
RawDoc(
id=f"{SOURCE_ID}:{rec['id']}",
source=SOURCE_ID,
fetched_at=fetched_at,
payload=rec,
url=rec.get("url"),
)
for rec in data["records"]
]
class <Name>Source:
id = SOURCE_ID
kind: Kind = SOURCE_KIND
def fetch(self, since: datetime | None = None) -> Iterable[RawDoc]:
if not SOURCE_URL:
raise NotImplementedError(
"Live fetch not wired: confirm the endpoint, then implement. "
"Use load_fixture() for offline runs."
)
raise NotImplementedError("Live fetch not implemented yet.")
def to_opportunities(
self, raw: RawDoc, now: datetime | None = None
) -> list[Opportunity]:
return to_opportunities(raw, now=now)
def load_fixture(self) -> list[RawDoc]:
return load_fixture()
register(<Name>Source())
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.
- 9d ago First seen · 181 lines · 87 tokens per session scan A 60e2eaf78e4e
add-a-source is a skill published in the GitHub repository mayai-it/bandiradar (2 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,584 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 2026-08-31.
Other skills, from other repositories
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
wikipedia
Search and read Wikipedia via x wkp — MediaWiki API, no API key, zero install; query, extract, suggest, and DDG route in one module. Load for wiki, wikipedia, encyclopedia lookup, article summary.
cve
Look up CVE records via x cve — cached, zero-API-key, daily xz TSV. Load for cve, vulnerability id, kev, epss, nvd, cvelist, or security advisory.
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…
scaffold-project
Scaffold a new app, API, backend, fullstack project, mobile app, polyglot service, monorepo, or starter with Better Fullstack. Use when the user wants to create, start, bootstrap, initialize, or generate a project from a stack description. Prefer the bundled Better Fullstack MCP server: guidance, schema…