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 Graphmaxer/gw1-mcp --skill gw1-build-assistantgit clone --depth 1 https://github.com/Graphmaxer/gw1-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/graphmaxer/gw1-mcp/gw1-build-assistant)<a href="https://agentmods.dev/skills/graphmaxer/gw1-mcp/gw1-build-assistant"><img src="https://agentmods.dev/badge/skills/graphmaxer/gw1-mcp/gw1-build-assistant/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/graphmaxer/gw1-mcp/gw1-build-assistant"><img src="https://agentmods.dev/badge/skills/graphmaxer/gw1-mcp/gw1-build-assistant.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 | $0.00127 | $0.01623 |
| Opus 5 | $0.00063 | $0.00812 |
| Sonnet 5 | $0.00025 | $0.00325 |
| Haiku 4.5 | $0.00013 | $0.00162 |
Grade A, and why
gw1-build-assistant 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 6d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GW1 Build Assistant
When to use this skill
Trigger when the user asks about Guild Wars 1 (the original game, not GW2):
designing or reviewing skill bars, decoding or producing template codes
(strings like OgCjkurIrSuXaXPXBYihygvlYcA), hero team composition,
skill lookups or comparisons, or pasting a paw-ned2 team blob
(pwnd0001...). The GW1 MCP tools are the source of truth for all game
data — it tracks the live Guild Wars Reforged balance, which differs from
historical wiki knowledge and from training data.
Hard rules
-
Template codes come ONLY from
encode_template. Never write, guess, reconstruct, or "remember" a code — hand-written codes are invalid in-game. -
After
encode_templatereturns a code, calldecode_templateon that exact code and confirm it matches the intended build before presenting it. -
Trust tool data over your own memory of the game. Skill stats and descriptions changed under Reforged; the tools reflect the current balance patch.
-
When a tool returns an error, read its message: it contains closest-match suggestions for misspelled skill or attribute names. Use them and retry instead of giving up or improvising. An empty suggestion list means the name was not close to anything — ask or search, do not guess.
-
The attribute point budget is non-linear, and it is the rule most often broken. A level 20 character has 200 points (170 base + 30 from quests). Cumulative cost to reach a rank:
rank 0 1 2 3 4 5 6 7 8 9 10 11 12 cost 0 1 3 6 10 15 21 28 37 48 61 77 97 So 12/12 already costs 194 and leaves 6 points. Three lines at 12 is 291 and impossible. A common legal spread is 12 / 10 / 8 = 195. Compute the total BEFORE calling
encode_template; the validator will otherwise reject it and you will have spent a round trip. Ranks here are base ranks 0-12 — runes and headgear are not part of the template.
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.
- 6d ago Changed · +10 lines f79774d958af
- 10d ago First seen · 106 lines · 127 tokens per session scan A e6a7c9dc40df
gw1-build-assistant is a skill published in the GitHub repository Graphmaxer/gw1-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 127 tokens to every session and 1,623 once invoked, about $0.0006 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
add-export
Add a new subpath export to the @cyanheads/mcp-ts-core package. Use when creating a new public API surface that consumers import from a dedicated subpath (e.g., @cyanheads/mcp-ts-core/newutil).
aba-precision-protocol
FOUNDATIONAL BEHAVIORAL PROTOCOL — ABA-based precision execution rules. Every prompt processed must follow these rules. Mistakes caught late create intermittent reinforcement of wrong patterns. Stop-fix-verify before proceeding.
add-provider
Add a new storage or service provider to the core package. Use when implementing a new backend for StorageService (e.g., a new database) or a new service provider (e.g., a new LLM backend).
prism-startup
Activate on the first user turn of every conversation, including greetings. Load Prism context using the user's configured project and quick, standard, or deep depth, then greet the developer by their configured agent name and show the matching recent-session context.
Verification Planner
Mandates generation of testassertions.json during planning. v7.2.0 enhanced with severity gates (warn/gate/abort), dependency chains, and Claw-as-Validator support.
add-mechanic
Add game mechanics with correct GDScript 4.x patterns -- movement, health, inventory, save/load.