Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add melodic-software/claude-code-plugins/plugin install gamingWrote 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/melodic-software/claude-code-plugins/dlss5)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/dlss5"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/dlss5/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/melodic-software/claude-code-plugins/dlss5"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/dlss5.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 | $0.00192 | $0.09696 |
| Opus 5.5 | $0.00077 | $0.03878 |
| Sonnet 5.5 | $0.00038 | $0.01939 |
| Haiku 4.5 | $0.00019 | $0.00970 |
Grade A, and why
dlss5 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 14d 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 — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Route a DLSS 5 mod request to one action. scripts/Invoke-Dlss5Mod.ps1 does the on-disk work:
eligibility probes, launcher discovery, the anti-cheat sources, snapshot, install, drift report,
byte-exact removal. This skill does what the script cannot: the ban and block research, the user's
confirmation and acknowledgement, the ledger rows, and tuning.
Windows only, PowerShell 7. Run /gaming:setup first: apply needs a provisioned fork build and
a runtime DLL under the data directory, and this skill never acquires either.
Resolving paths (do this first)
Resolve each option here, before composing any command, so the command line carries a literal path or nothing.
| Parameter | Resolution |
|---|---|
Data directory (-DataDir) |
${user_config.data_dir} when set to a non-empty path. If it is empty or still shows an unexpanded ${user_config.data_dir} token (option unset), omit -DataDir: the script defaults to Gaming\dlss5 under the user's Documents folder and follows a OneDrive-redirected Documents, which a hand-built path does not |
Runtime DLL (-RuntimeDll) |
${user_config.runtime_dll} when set to a non-empty path. If it is empty or still an unexpanded token, omit -RuntimeDll: the script defaults to runtime\nvngx_dlssnr.dll under the data directory |
Never type an option token onto a command line. An unset option survives substitution as its own token, and Bash rejects it as a bad substitution before the script starts.
When the ledger path is needed and the data directory option is unset, get the default from the
native side: pwsh -NoProfile -Command "Join-Path ([Environment]::GetFolderPath('MyDocuments')) Gaming\dlss5".
When the data directory is the default, the script refuses every verb but refetch and
selftest while the legacy Documents\Gaming\state\ has entries and the new default's state\
has none. Relay the move it names verbatim; never move the files yourself.
What ships with it
14 files 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.
- evals/evals.json 20 KB
- presets/_base.json 16 B
- presets/007-first-light.json 1.4 KB
- presets/cyberpunk-2077.json 1.4 KB
- reference/anticheat-posture.md 15 KB
- reference/candidate-selection.md 11 KB
- reference/fork-comparison.md 6.7 KB
- reference/launchers.md 8.9 KB
- reference/presets.md 17 KB
- reference/reversal-matrix.md 5.9 KB
- reference/tuning-guide.md 4.9 KB
- reference/upstream-watch.md 6.8 KB
- scripts/Invoke-Dlss5Mod.ps1 178 KB runs code
- scripts/Invoke-Dlss5Mod.test.sh 730 B runs code
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.
- 14d ago Changed · +20 lines 7fca1c26b692
- 16d ago Changed · -1 lines 059528fbac68
- 17d ago Changed · +1 lines 5a3dfd29fb8f
- 18d ago Changed · +7 lines caa2a1263f8a
- 21d ago Changed · +79 lines · +16 tokens per session d056646059d7
- 22d ago First seen · 378 lines · 176 tokens per session scan A 8f7c72651a50
dlss5 is a skill published in the GitHub repository melodic-software/claude-code-plugins (25 stars, last pushed today), licensed MIT. It adds 192 tokens to every session and 9,696 once invoked, about $0.0008 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 2026-09-24.
Other skills, from other repositories
find-shortest-path
For pathfinding and search: shortest path, maze solving, game AI, route planning, graph traversal, BFS/DFS, Dijkstra, A problems.
stack-based-backtrack
For search with undo: explicit decision stack, backtracking when paths fail, depth-first exploration with state restoration.
solve-grid-maze
For 2D grid problems: mazes, board games, tile maps, pixel grids, coordinate systems, cellular automata, flood fill. Uses dict-based Grid class pattern.
use-sparse-set
For sparse data: infinite grids, large spaces with few active elements, membership testing, set operations on coordinates or states.
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
parallel-worker
Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.