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 CitiesSkylinesModding/agents-plugins --skill gameface-updategit clone --depth 1 https://github.com/CitiesSkylinesModding/agents-pluginsWrote 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/citiesskylinesmodding/agents-plugins/gameface-update)<a href="https://agentmods.dev/skills/citiesskylinesmodding/agents-plugins/gameface-update"><img src="https://agentmods.dev/badge/skills/citiesskylinesmodding/agents-plugins/gameface-update/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/citiesskylinesmodding/agents-plugins/gameface-update"><img src="https://agentmods.dev/badge/skills/citiesskylinesmodding/agents-plugins/gameface-update.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 | $0.00067 | $0.02170 |
| Opus 5.5 | $0.00027 | $0.00868 |
| Sonnet 5.5 | $0.00013 | $0.00434 |
| Haiku 4.5 | $0.00007 | $0.00217 |
Grade A, and why
gameface-update 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 26d 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.
`curl -s https://docs.coherent-labs.com/cpp-gameface/changelog/feature/` into `.scratch/gameface-update-<new>/`, and parse the saved page there: a summarising fetch tool returns the range abridged. Inside `<main>`, a rel How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sweeping the gameface plugin for an engine update
This skill re-probes every version-dependent claim against the running game, reads the rest off Coherent's feature changelog, and ends with every Verified against Cohtml line on the new version.
It edits plugins/coherent-gameface/, docs/ROADMAP.md and the probe catalogue. The research files' observed-Cohtml lines, docs/SOURCES.md and all cs2-modding prose are cs2-game-update's.
A stale ceiling alone is a shorter run. It applies where mise skills:check-changelog is red and the two versions below are equal, and comparing them needs no game. Fetch the changelog, work the timeline-and-ceiling step, run the checks, then take the close's review pause before committing it as fix(coherent-gameface):. The refusal, the plan and the rest of the close belong to a moved engine.
1. Reach the game, or refuse
Outside the ceiling-only run above, game_status is the first act. Unreachable ends the run: say the sweep needs the reference target running with its CDP endpoint answering, and stop there. Every claim this sweep writes is a probed one, so the run ends here rather than requesting a launch or continuing from the docs.
Anything a later step needs done in the game — a save loaded, a panel opened, a setting changed — takes the root AGENTS.md ask-before-acting rule: say what and why, last in the message, and end the turn.
2. Fix the two versions
- New:
AssemblyVersioninsrc/cohtml.Net/Properties/AssemblyInfo.csat HEAD of the decompile root~/.cs2-modding/setup.mdrecords. - Old: the version every baseline line states —
grep -rho 'Verified against Cohtml [0-9.]*[0-9]' plugins/coherent-gameface/skills | sort -ureturns one line, and a second one means a previous sweep never closed: resume it before starting this one.
Equal versions mean nothing to sweep: work the ceiling-only run above where the ceiling is stale, and otherwise say so and stop.
The Browser string game_status reported must carry the new version. Where it carries another, the decompile and the running game disagree: report both and stop.
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.
- 26d ago First seen · 76 lines · 67 tokens per session scan A 5f4349cbd77b
gameface-update is a skill published in the GitHub repository CitiesSkylinesModding/agents-plugins (7 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 2,170 once invoked, about $0.0003 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 2026-09-20.
Other skills, from other repositories
frame-rate-stability
Use when a rendering path needs stable frame-time, CPU, GPU, and memory evidence against fixed targets. Not for one-shot profiling or visual quality review.
mastering-engineer
Guides audio mastering for streaming platforms including loudness optimization and tonal balance. Use when the user has approved tracks and wants to master audio files.
promo-writer
Generates platform-specific social media copy from album themes, track concepts, and lyrics. Use when promo/ templates need to be populated before release.
researcher
Conducts investigative-grade research with primary source analysis, cross-verification, and trial-level depth. Use when an album needs factual research, source material, or verification of claims.
session-start
Runs the session startup procedure - verifies setup, loads config and state, checks skill models, and reports project status. Use at the beginning of a fresh session.
validate-album
Validates album directory structure, file locations, and content integrity. Use before release or whenever the user wants to check an album's structural health.