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 chrischall/alltrails-mcp --skill alltrails-fpxgit clone --depth 1 https://github.com/chrischall/alltrails-mcpWrote 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/chrischall/alltrails-mcp/alltrails-fpx)<a href="https://agentmods.dev/skills/chrischall/alltrails-mcp/alltrails-fpx"><img src="https://agentmods.dev/badge/skills/chrischall/alltrails-mcp/alltrails-fpx/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/chrischall/alltrails-mcp/alltrails-fpx"><img src="https://agentmods.dev/badge/skills/chrischall/alltrails-mcp/alltrails-fpx.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 | $0.00099 | $0.01573 |
| Opus 5.5 | $0.00040 | $0.00629 |
| Sonnet 5.5 | $0.00020 | $0.00315 |
| Haiku 4.5 | $0.00010 | $0.00157 |
Grade A, and why
alltrails-fpx 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
the HTTP client, not just the cookie — a Node/curl replay of a captured How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AllTrails via fpx (no MCP)
AllTrails has no public API; alltrails-mcp reverse-engineers the internal
one alltrails.com itself uses, fronted by DataDome. DataDome fingerprints
the HTTP client, not just the cookie — a Node/curl replay of a captured
cookie gets 403'd even the same day an identical in-tab fetch succeeds.
So every request must ride a same-origin fetch inside the user's own signed-in
tab, which fpx provides (no stored-cookie mode, unlike some other fleet
skills).
Every request also needs an x-at-key app header — a static, anonymous
client-identifier the web app sends on every /api/alltrails/* call. It is
not stored anywhere — capture it live from the tab's own traffic (below).
An in-tab fetch does not add it automatically, so it (plus
x-at-caller/x-language-locale) must be attached explicitly on every fpx
call, same as the MCP's client.ts does.
One-time setup
npm install -g @fetchproxy/cli # provides `fpx`
fpx profile add alltrails --domain alltrails.com
fpx profile declare alltrails \
--capture-header '[email protected]/api/alltrails/*'
fpx pair -p alltrails # prints a pair code → approve in ContextMint Bridge
Requirements: the ContextMint Bridge browser extension installed
(releases —
Chrome: load the chrome zip unpacked; use Chrome for now — Safari will ship inside the
ContextMint app, which has no public download yet), its Chrome
Site access allowing alltrails.com, and an open, signed-in
www.alltrails.com tab (the per-user tools need a real session; the trail
tools work signed-out too). Pairing persists after the first approval.
ContextMint Bridge is the fetchproxy extension renamed, same maintainer; source and .sha256-checkable release zips at https://github.com/nullnet-app/contextmint-bridge.
Capture the app key, then attach it on every call
x-at-key is captured from the tab's own API traffic — the capture only
fires while the tab makes a request. fpx session triggers the capture and
returns everything declared, including capturedHeaders:
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.
- 1mo ago Changed · +4 lines c5b945b4394e
- 2mo ago Changed · +7 lines 024b182a268c
- 2mo ago First seen · 112 lines · 99 tokens per session scan A d9ca17ec3916
alltrails-fpx is a skill published in the GitHub repository chrischall/alltrails-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 99 tokens to every session and 1,573 once invoked, about $0.0004 per session on Opus 5.5. 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.
alltrails-fpx compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| alltrails-fpxchrischall/alltrails-mcp | Skill | 0 | 3d ago | MIT | A | 99 | Claude Code |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 8d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |