Agent skill

Source Watch

by amd in amd/gaia

Check a web page or feed for something worth telling the user about, remembering what was already reported so nothing repeats.

MITAuto-check passed

Install Source Watch

skills CLI
$ npx skills add amd/gaia --skill source-watch -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install amd/gaia source-watch --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/amd/gaia.git skills-src && mkdir -p .claude/skills && cp -r skills-src/hub/skills/source-watch .claude/skills/source-watch && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
source-watch
GitHub stars
1.6k
Token cost
~698 tokens
SKILL.md length
353 words
Files
1
Skills in repo
44
Repo updated
First seen
Licence
MIT

At a glance

Check a web page or feed for something worth telling the user about, remembering what was already reported so nothing repeats.

  • Works in 6 steps: Recall what was already reported. → Fetch the source. fetch_page(url). If… → Extract the candidate items. Titles,… → …
  • The user asks to watch
  • SKILL.md covers Configure, Procedure, Honest limits and Fork this
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Source Watch is an agent skill from amd/gaia. Check a web page or feed for something worth telling the user about, remembering what was already reported so nothing repeats. Use when the user asks to watch, monitor, or check a URL for changes, new items, or a condition being met.

Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Build AI agents for your PC. The licence is MIT.

When your agent uses it

  • The user asks to watch
  • Check a URL for changes
  • A condition being met

Example prompts

  • “/source-watch”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Recall what was already reported.
  2. Fetch the source. fetch_page(url). If the fetch fails, report the
  3. Extract the candidate items. Titles, versions, prices, listings —
  4. Apply the match, then drop every item whose identifier already appeared in
  5. Report or stay quiet. If nothing new matched, say "no new matches" in one
  6. Record what you reported.

What it can do on your machine

Read from SKILL.md and the folder at commit 6c3bb5c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Source Watch loads about 698 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 353 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~698

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from amd/gaia at commit 6c3bb5c, republished under its MIT licence (© amd). 353 words, ~698 tokens.

Download SKILL.mdSave it as .claude/skills/source-watch/SKILL.md (or your agent's skills folder).
name
source-watch
description
Check a web page or feed for something worth telling the user about, remembering what was already reported so nothing repeats. Use when the user asks to watch, monitor, or check a URL for changes, new items, or a condition being met.
license
MIT
version
1.0.0

Source Watch

The generic watcher. Fetch a source, decide whether anything matches, suppress what was already reported, and say something only when there is news. Every other watcher in this pack is a fork of this one.

Configure

The user supplies these; ask for any that are missing before the first run.

SettingMeaningExample
SourceThe URL to fetchhttps://example.com/releases
MatchWhat counts as interesting"any version above 3.0"
Memory keyWhere seen items are recordedwatch:example-releases

Procedure

  1. Recall what was already reported. recall(query="<memory key>", limit=50). This is what stops the watcher telling the user the same thing every run.
  2. Fetch the source. fetch_page(url). If the fetch fails, report the failure and stop — an empty page is not "no news", and treating it as such is how a watcher silently dies.
  3. Extract the candidate items. Titles, versions, prices, listings — whatever the source is a list of. Keep a stable identifier per item so step 4 can compare across runs.
  4. Apply the match, then drop every item whose identifier already appeared in step 1.
  5. Report or stay quiet. If nothing new matched, say "no new matches" in one line. Do not pad a quiet run into a paragraph.
  6. Record what you reported. remember(fact="<memory key>: <identifier> — <one-line summary>", category="fact") for each new item, so the next run suppresses it.
Show full SKILL.md (129 more words)Show less

Honest limits

  • This runs when you ask it to. GAIA's scheduler can run a recurring prompt (gaia schedule add --cron ... --prompt ...), but it cannot yet run a skill on a schedule — --skill is rejected at creation time. Until that is wired, "watching" means you invoke the skill and it checks.
  • Step 1 and step 6 need memory enabled. If the recall / remember tools are absent, the watcher still works but repeats itself every run — say so rather than pretending it de-duplicated.
  • Fetch only pages you are allowed to poll, and do not hammer a source.

Fork this

Copy the directory, rename it and its name field, then specialize step 3 (what an item is) and step 4 (what counts as interesting). price-watch in this pack is exactly that fork.

© amd, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in hub/skills/source-watch of amd/gaia.

Open the folder on GitHubat commit 6c3bb5c

Compare with similar skills

Source Watch next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Source Watch compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Source Watch this skillamd/gaia1.6k—~698Automated safety check: PassMIT
Canary Watchaffaan-m/ECC274k1 repos~770Automated safety check: PassMIT
Canary Watchaffaan-m/ECC274k—~405Automated safety check: PassMIT
Canary Watchaffaan-m/ECC274k—~414Automated safety check: PassMIT
Watchtaoufik123-collab/claude-watch930—~5.8kAutomated safety check: WarnMIT
Feedsalsk1992/CloddsBot2.9k—~1.8kAutomated safety check: PassMIT

Similar skills

  • Canary Watch

    affaan-m/ECC

    A skill your agent uses to monitor and verify a deployed URL after releases — checks HTTP endpoints, SSE streams, static assets, console errors, and performance regressions after deploys, merges, or…

    274k GitHub starsUsed in 1 repo~770 tokens
    DevOps & CloudAuto-check passed
  • Canary Watch

    affaan-m/ECC

    このスキルを使用して、デプロイメント、マージ、または依存関係アップグレード後にデプロイされたURLの回帰を監視します. An agent skill from affaan-m/ECC.

    274k GitHub stars~405 tokensUpdated 2 days ago
    DevOps & CloudAuto-check passed
  • Canary Watch

    affaan-m/ECC

    使用此技能在部署、合并或依赖升级后监控已部署的URL是否存在回归问题。

    274k GitHub stars~414 tokensUpdated 2 days ago
    DevOps & CloudAuto-check passed
  • Watch

    taoufik123-collab/claude-watch

    Watch a video (URL or local path) like an editor. An agent skill from taoufik123-collab/claude-watch.

    930 GitHub stars~5.8k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check: warnings
  • Feeds

    alsk1992/CloddsBot

    Real-time market data feeds from 8 prediction market platforms

    2.9k GitHub stars~1.8k tokensUpdated 4 days ago
    Business, Finance & HRAuto-check passed
  • Watch

    gooseworks-ai/goose-skills

    Watch a rendered video (whole file or specific ranges) at a chosen fidelity and emit a timestamp-keyed observation report.

    1.2k GitHub starsUsed in 1 repo~1k tokens
    Media & CreativeAuto-check passed

More from amd/gaia

All 44 skills in this repo
  • Adds a release eval scorecard to a GAIA hub agent by writing a harness adapter, running a real eval, and wiring the result into the agent's README and release gate.

    1.6k GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • Walks through releasing a GAIA sidecar agent as a frozen binary plus npm client through the tag-triggered Agent Hub CI pipeline, with a human gate before publishing.

    1.6k GitHub stars~3.6k tokensUpdated today
    Auto-check passed
  • Mines local Claude Code session transcripts with a deterministic Python pipeline to show what the agent is actually used for, how often it fails and what it costs.

    1.6k GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Benchmarks AMD's GAIA agent against Claude Code and across models on quality, honesty, steps, tokens, time and real cost, using gaia eval tasks.

    1.6k GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Guides safe code changes by finding the right file with grep or semantic search, reading before editing, reproducing bugs first, and proving a fix with a real test run.

    1.6k GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Walks through scaffolding, writing and testing a new GAIA agent as a Python class with the SDK, from the base Agent subclass to registered tool methods.

    1.6k GitHub stars~1.5k tokensUpdated today
    Auto-check passed

Questions about Source Watch

What does Source Watch do?

Check a web page or feed for something worth telling the user about, remembering what was already reported so nothing repeats. Source Watch is an agent skill from amd/gaia. Check a web page or feed for something worth telling the user about, remembering what was already reported so nothing repeats.

When should I use Source Watch?

Source Watch fits situations like: the user asks to watch; check a URL for changes; A condition being met.

How do I install Source Watch in Claude Code?

Run `npx skills add amd/gaia --skill source-watch -a claude-code`. Or copy the skill folder (hub/skills/source-watch in amd/gaia) into .claude/skills/source-watch in your project. Claude Code loads it when a task matches its description.

How do I install Source Watch in Codex?

Run `npx skills add amd/gaia --skill source-watch -a codex`. Or copy the skill folder (hub/skills/source-watch in amd/gaia) into .agents/skills/source-watch in your project. Codex loads it when a task matches its description.

Can I use Source Watch in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add amd/gaia --skill source-watch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/source-watch, .gemini/skills/source-watch, .github/skills/source-watch and .opencode/skills/source-watch in your project.

What does Source Watch need to run?

SKILL.md names no scripts, command-line tools or credentials: Source Watch is instructions for the agent only.

Does Source Watch access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Source Watch safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Source Watch use?

Source Watch is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Source Watch use?

About 698 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Source Watch?

Skills that share tags, products or a category with Source Watch: Canary Watch (affaan-m/ECC, 274k stars), Canary Watch (affaan-m/ECC, 274k stars), Canary Watch (affaan-m/ECC, 274k stars) and Watch (taoufik123-collab/claude-watch, 930 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Source Watch?

amd (a GitHub organization) maintains it in amd/gaia, which has 1,580 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on October 6, 2026.

Source: amd/gaia on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.