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 agentmods add skills/onewave-ai/open-agent-stack/watch-competitorsnpx skills add OneWave-AI/open-agent-stack --skill watch-competitorsgit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWrote 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/onewave-ai/open-agent-stack/watch-competitors)<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/watch-competitors"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/watch-competitors.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.00517 |
| Opus 5 | $0.00034 | $0.00259 |
| Sonnet 5 | $0.00013 | $0.00103 |
| Haiku 4.5 | $0.00007 | $0.00052 |
Grade A, and why
watch-competitors 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watch Competitors
Fetch the current state of competitor pages, diff against a stored baseline, report changes with sources, then update the baseline.
This skill requires web access. Use the built-in web search and fetch tools; no API key is needed.
Workflow
-
Resolve the target list. Take competitor names or URLs from the user. For each name without a URL, search the web to find the canonical domain. Confirm the homepage, pricing page, and content surface (blog, changelog, or newsroom) for each.
-
Load the baseline. Read
references/baseline.jsonif it exists. If it is missing, treat this as a first run with no prior state and note that the report will be a baseline capture, not a diff. -
Capture current state. For each competitor, fetch the homepage, pricing page, and content surface. Record for each page: the headline messaging, listed plans and prices, plan features, and the titles and dates of the most recent content items. Keep the source URL for every captured fact.
-
Diff against baseline. For each competitor, compare current state to the stored snapshot. Identify: pricing changes (amount, plan name, billing terms), new or removed plans, messaging or positioning shifts, new pages, removed pages, and newly published content since the last run.
-
Report the diff. Produce a per-competitor summary. Lead with material changes (pricing, plans, launches), then secondary changes (messaging, content). Cite the source URL for each change. If nothing changed for a competitor, state that explicitly. On a first run, report the captured baseline instead.
-
Update the baseline. Write the current captured state back to
references/baseline.jsonso the next run diffs against it. Stamp each competitor entry with the capture date.
Notes
- Always attach a source URL to every reported fact; never report a change you cannot point to.
- Distinguish a real change from a page you simply could not reach. If a fetch fails, flag it as unverified rather than as a removal.
- See
references/baseline-schema.mdfor the baseline file structure.
What ships with it
1 file 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.
- 5d ago First seen · 31 lines · 67 tokens per session scan A e5e22274cd18
watch-competitors is a skill published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 25d ago), licensed MIT. It adds 67 tokens to every session and 517 once invoked, about $0.0003 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.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
flash-attention
Speed up long-sequence transformer training and inference.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
grounded-citations
Ground answers and documents in cited, verifiable sources.
openhands
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).
duckduckgo-search
Free keyless web, news, and image search via ddgs.