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 elleryfamilia/loadout --skill loadout-remembergit clone --depth 1 https://github.com/elleryfamilia/loadoutWrote 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/elleryfamilia/loadout/loadout-remember)<a href="https://agentmods.dev/skills/elleryfamilia/loadout/loadout-remember"><img src="https://agentmods.dev/badge/skills/elleryfamilia/loadout/loadout-remember/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/elleryfamilia/loadout/loadout-remember"><img src="https://agentmods.dev/badge/skills/elleryfamilia/loadout/loadout-remember.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 67 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00093 | $0.01239 |
| Opus 5 | $0.00046 | $0.00620 |
| Sonnet 5 | $0.00019 | $0.00248 |
| Haiku 4.5 | $0.00009 | $0.00124 |
Grade A, and why
loadout-remember 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 9d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remember durable guidance in loadout
loadout injects the user's global agent guidance from
~/.config/loadout/config.toml: reusable fragments composed into
stack-targeted profiles. When the user states a preference that should
outlive this session and this project, the right home for it is a fragment —
not a repo CLAUDE.md, and not your agent-local memory.
Read reference.md for the exact TOML schema before editing.
Decision boundary — when this skill applies
Apply the test in order; stop at the first match:
- Project- or session-specific? ("this repo uses pnpm", "call it Foo in this PR") → your normal memory / the repo's own files. Not this skill.
- A fact, not guidance? (who the user is, an URL, a deadline) → normal memory. Not this skill.
- Durable cross-project guidance that contradicts or refines something the loadout context block already says? → edit that fragment (the strongest signal: the user is correcting guidance loadout itself injected).
- Durable cross-project guidance with no matching fragment? → offer a new fragment (and ask which profiles should compose it).
When unsure whether it's durable or global, ask the user one short question rather than guessing. Saving to loadout and your own memory is redundant — prefer loadout for anything that passes the test, since it reaches every agent.
Orientation (run these probes first)
# loadout on PATH?
command -v loadout >/dev/null 2>&1 && loadout --version || echo "NOT INSTALLED — stop; suggest installing loadout"
# Current fragments (ids + descriptions)
load fragments 2>/dev/null
# The active profile for this repo (what's actually injected here)
load explain 2>/dev/null | head -40
Also check the loadout context block already in your conversation (it starts with "What is loadout?" / "loadout snapshot") — the section headings there map to fragment descriptions, which tells you which fragment the user is correcting.
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.
- 9d ago First seen · 97 lines · 93 tokens per session scan A 0fd3bec50729
loadout-remember is a skill published in the GitHub repository elleryfamilia/loadout (29 stars, last pushed 23d ago), licensed MIT. It adds 93 tokens to every session and 1,239 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
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
brief
Brief the user on what they saved in a period — the thread running through it, not a list.
resurface
Pick a few old saves worth revisiting now, and say why now.
atomicmemory
Persistent semantic memory across Claude Code sessions — user preferences, project context, prior decisions, codebase facts. Call memorysearch before answering questions that reference past work. Call memoryingest after the user shares durable facts.
atomicmemory-cli
Use the installed AtomicMemory CLI for memory search, ingestion, packaging, diagnostics, and agent-safe JSON output.
agent-context
Create, validate, and maintain a structured .agent-context directory for a repository so AI agents navigate the codebase efficiently and make higher-quality decisions. Use when setting up agent context for a new repo, updating context after agent work, or catching up context after human work.