add-source

add-source is a skill for Claude Code from Miracle-Aligner/job-search-hq. It costs 101 tokens per session (593 once invoked), scanned A, original, MIT.

A procedure for changing the job-listing websites and filters used by a recurring listings sweep.

In plain words
What is it for?
Use it to add, edit, disable, or remove job sources, set authentication and filters, or pass a list of job links directly for bulk parsing.
Why use it?
It keeps source settings in one configuration file and avoids treating fragile website selectors as permanent configuration.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Part of the job-search-hq plugin — 9 skills shipped together

Good fit Use it to add, edit, disable, or remove job sources, set authentication and filters, or pass a list of job links directly for bulk parsing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/miracle-aligner/job-search-hq/add-source
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.

Any agent
npx skills add Miracle-Aligner/job-search-hq --skill add-source
Clone the repo
git clone --depth 1 https://github.com/Miracle-Aligner/job-search-hq

Made for: Claude Code.

Or install job-search-hq, the plugin that ships this one along with the rest of its 9 skills.

Wrote 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.

agentmods badge for add-source

README.md
[![agentmods](https://agentmods.dev/badge/skills/miracle-aligner/job-search-hq/add-source/github.svg)](https://agentmods.dev/skills/miracle-aligner/job-search-hq/add-source)
Your own site
<a href="https://agentmods.dev/skills/miracle-aligner/job-search-hq/add-source"><img src="https://agentmods.dev/badge/skills/miracle-aligner/job-search-hq/add-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.

agentmods 80×15 button for add-source

Your own site · 80×15
<a href="https://agentmods.dev/skills/miracle-aligner/job-search-hq/add-source"><img src="https://agentmods.dev/badge/skills/miracle-aligner/job-search-hq/add-source.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 593 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00101 $0.00593
Opus 5 $0.00051 $0.00296
Sonnet 5 $0.00020 $0.00119
Haiku 4.5 $0.00010 $0.00059

Measured 10d ago against content hash d9239f93fd07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

add-source scanned grade A with 0 findings 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 10d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/add-source/SKILL.md · 56 lines

What it actually says

add-source

config/sources.json is the single source of truth for where /refresh-listings looks. This skill edits it; no skill-prose changes needed.

Add / edit a source

Append or modify an entry in sources[]:

{
  "name": "Indeed",
  "platform": "Indeed",
  "auth": false,
  "enabled": true,
  "urls": ["https://www.indeed.com/q-ai-engineer-jobs.html"],
  "filters": { "categories": [], "expRange": [] }
}
  • enabled: false keeps the config but skips it on a sweep.
  • auth: true means it needs the user's logged-in session in Claude in Chrome.
  • If the platform is new, also add it to config/platforms.json (see the platform note in the README) so cards/filter colour-code it.
  • Selectors are NOT config — they rot. /refresh-listings adapts selectors at runtime; only stable bits (URLs, auth, filters, title-noise) live here.

If the user would rather hand you a list of job URLs than configure sweeps, don't use /refresh-listings or sources at all — pass the links straight to /add-vacancy (bulk mode). Sources config is only for recurring sweeps. You can also set crossLink: false (below) to keep the board to exactly the links given, with no alt-source lookup.

Toggles

  • crossLink (top level, default true): when false, /add-vacancy skips the "find the same role on other platforms" step and won't populate altLinks. Set false if the user wants only the exact links they provide.
  • titleNoise: the case-insensitive regex of titles to drop before assessment. Edit to tune.

Finish

No bake needed — sources.json is read by the skills, not the viewer. Confirm the change and run python3 scripts/validate.py data/vacancies.sample.json only if you also touched platforms.

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. 10d ago First seen · 56 lines · 101 tokens per session scan A d9239f93fd07

Subscribe to this mod's changes

add-source is a skill published in the GitHub repository Miracle-Aligner/job-search-hq (1 stars, last pushed 3mo ago), licensed MIT. It adds 101 tokens to every session and 593 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.