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 skillmds/skillmd --skill competitor-watch-track-a-competitor-ping-on-real-movesgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/competitor-watch-track-a-competitor-ping-on-real-moves)<a href="https://agentmods.dev/skills/skillmds/skillmd/competitor-watch-track-a-competitor-ping-on-real-moves"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/competitor-watch-track-a-competitor-ping-on-real-moves/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/skillmds/skillmd/competitor-watch-track-a-competitor-ping-on-real-moves"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/competitor-watch-track-a-competitor-ping-on-real-moves.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 | $0.00012 | $0.00578 |
| Opus 5.5 | $0.00005 | $0.00231 |
| Sonnet 5.5 | $0.00002 | $0.00116 |
| Haiku 4.5 | $0.00001 | $0.00058 |
Grade A, and why
Competitor Watch — track a competitor, ping on real moves 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 1mo 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.
What it actually says
Competitor Watch
Does: tracks what a named competitor is shipping and pings you only on real moves. Solves: finding out about a competitor's launch a month late. Triggers on: "watch [competitor] and tell me what changes"
How Maxim does this
Routes to competitive-intel-analyst + web sources, compares against the last snapshot, and reports only real moves since — launches, pricing changes, positioning shifts — not noise. Each move gets a so-what (does it threaten your moat?), grounded in Porter / 7 Powers.
Behavioral overlay
- Frameworks (cited per ADR-007): Porter's Five Forces · 7 Powers · signal detection (real move vs. PR noise).
- No-fabrication is load-bearing: verified moves are stated as fact with the source; anything inferred (e.g. "likely targeting enterprise") is marked inference. Default 🟡 MEDIUM for that reason.
The unattended "monitor" version
orchestrator/workflows/competitor-watch.mjs — the read-only Workflow #2 from the standard: scheduled, dry-run-default, idempotent (won't re-report the same move), bounded + logged. Read-only, so it never acts — it only surfaces. Go-live just turns on the morning delivery.
Output
Moves since last check (launch / pricing / positioning) · significance vs. your moat · sources · fact vs. inference marked.
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.
- 1mo ago First seen · 49 lines · 12 tokens per session scan A 30b490fa8654
Competitor Watch — track a competitor, ping on real moves is a skill published in the GitHub repository skillmds/skillmd (143 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 578 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-19.
Competitor Watch — track a competitor, ping on real moves compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Competitor Watch — track a competitor, ping on real movesskillmds/skillmd | Skill | 143 | 4d ago | MIT | A | 12 | Claude Code |
| sloplessberelevant-ai/slopless | Skill | 339 | 3d ago | MIT | A | 40 | Claude Code, Codex |
| suikonwiizo/suiko | Skill | 115 | yesterday | MIT | A | 192 | Codex |
| poly-lint-and-formatGoldziher/poly | Skill | 20 | today | MIT | A | 42 | Claude Code |
| poly-orchestratorGoldziher/poly | Skill | 20 | today | MIT | A | 43 | Claude Code |
| poly-mcpGoldziher/poly | Skill | 20 | today | MIT | A | 38 | Claude Code |
| poly-tiers-and-scopeGoldziher/poly | Skill | 20 | today | MIT | A | 60 | Claude Code |