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 SummerEngine/summer-engine-agent --skill auto-fire-targetinggit clone --depth 1 https://github.com/SummerEngine/summer-engine-agentWrote 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/summerengine/summer-engine-agent/auto-fire-targeting)<a href="https://agentmods.dev/skills/summerengine/summer-engine-agent/auto-fire-targeting"><img src="https://agentmods.dev/badge/skills/summerengine/summer-engine-agent/auto-fire-targeting/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/summerengine/summer-engine-agent/auto-fire-targeting"><img src="https://agentmods.dev/badge/skills/summerengine/summer-engine-agent/auto-fire-targeting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00092 | $0.02122 |
| Opus 5 | $0.00046 | $0.01061 |
| Sonnet 5 | $0.00018 | $0.00424 |
| Haiku 4.5 | $0.00009 | $0.00212 |
Grade A, and why
auto-fire-targeting 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- auto-fire-targeting — 88% identical, 27 lines differ
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-Fire Weapon Targeting — pending-damage pattern
A survivors-genre auto-fire weapon picks a target each fire frame. Naive nearest-enemy targeting wastes bullets when fire rate exceeds bullet flight time. This skill encodes the pending-damage pattern that fixes it.
The problem
Auto-fire weapon. Bullet speed 22 m/s. Target 10m away. Bullet takes ~0.45s to arrive. With high attack speed the player fires several bullets per second. By the time the first bullet arrives and kills the target, several more bullets are already in flight toward where the target was. They miss into empty space. The player sees bullets "fan out in a cone past the dead enemy" while other enemies stand around untouched.
This is not a re-targeting bug. The weapon's _fire() correctly re-runs find_nearest_enemy() each shot. The issue is that the target is alive at fire-time and dead at arrival-time. All shots fired in that window aim at it because none of them know about the kill in flight.
The fix — pending damage commitment
Each enemy carries a counter of damage that is in flight toward it. Targeting de-prefers (but does not exclude) enemies whose pending damage already exceeds their current HP.
1. Add the counter to the enemy base class
# enemy_base_3d.gd
var pending_damage: float = 0.0
func commit_pending(amount: float) -> void:
pending_damage += amount
func release_pending(amount: float) -> void:
pending_damage = maxf(0.0, pending_damage - amount)
## True if enough damage is already in flight to kill this enemy.
func is_saturated() -> bool:
return pending_damage >= health
2. Update the targeting helper
The selector keeps the saturated set as a fallback. If every enemy is saturated, the player must still be able to fire on someone — fall through to a normal nearest pick across saturated enemies. Otherwise prefer non-saturated.
# targeting.gd
static func pick(origin: Vector3, mode: int, max_range: float, ...) -> Node3D:
var enemies: Array = GameManager.get_enemies()
var best: Node3D = null
var best_score: float = -INF
var fallback: Node3D = null
var fallback_score: float = -INF
for enemy in enemies:
# ... existing range + LoS filters ...
var score := _score(enemy, d_sq, mode)
var saturated: bool = "is_saturated" in enemy and enemy.is_saturated()
if saturated:
if score > fallback_score:
fallback_score = score
fallback = enemy
else:
if score > best_score:
best_score = score
best = enemy
if best != null:
return best
return fallback # everyone is saturated; fire on the next-best anyway
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.
- 10d ago First seen · 196 lines · 92 tokens per session scan A 6b8d15fc0043
auto-fire-targeting is a skill published in the GitHub repository SummerEngine/summer-engine-agent (59 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 2,122 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
self-evolve
Capture reusable patterns from a finished project and lift them into framework-level priors (contracts, modules, skeletons) that future projects inherit. Run only when the user explicitly requests self-evolution; the orchestrator executes the workflow.
artist-self-evolve
Distill stable art-generation patterns from a completed project, so future projects produce comparable assets without re-discovering the prompts. Lead-dispatched only — orchestrator invokes this skill from its self-evolve flow with a game-slug message; do not self-trigger.
vibegame-build
Run VibeGame's standard end-to-end game development workflow with reviewer gates. Use when the user wants to create a game from zero or evolve an existing game across multiple stages.
vibegame-start
Resume a VibeGame orchestrator session after vibegame start. Use at the beginning of a Claude or Codex session to inspect team runtime state, repair missing persistent members, load goal and GDD context, inspect tasks, and ask the user what to do next.
vibegame-edit
Iterate broadly on an existing game, on top of vibegame-build. Use when the user asks to change an existing game's art style, genre, or core rules. Not for local tuning such as numbers or game feel. Orchestrator only.
hearth-feel
Make a Hearth game feel good, not just run — the juice stack (hit-stop, screen shake, flash, particle bursts, layered sound), tween easing, camera effects, anticipation/recovery animation idioms, game-UX conventions (menus, pause, onboarding, difficulty, save etiquette), effect-asserting playtests, and the quality bar…