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 agentmods add skills/heapy/kortex/amnesianpx skills add Heapy/kortex --skill amnesiagit clone --depth 1 https://github.com/Heapy/kortexWhat 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 | $0.00090 | $0.00448 |
| Opus 5 | $0.00045 | $0.00224 |
| Sonnet 5 | $0.00018 | $0.00090 |
| Haiku 4.5 | $0.00009 | $0.00045 |
Grade A, and why
amnesia 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 yesterday.
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.
What it actually says
Amnesia
Overview
Reorient the user after they stepped away. Report what the session is, where it left off, and what changed while they were gone.
Answer from the conversation already in context. Do not re-run builds, re-read files, or start new work to produce this recap.
Output
Report these four sections, in order.
Session started
When this session began. Use timestamps available in the conversation context. If no timestamp is available, say so plainly instead of guessing — an approximation stated as fact is worse than "unknown".
Last user message
When the user last wrote, and the verbatim text of that message — the one before this request, not this request itself. Quote it; do not paraphrase. If it was long, quote the first few lines and mark it as truncated.
Since then
What happened after that message: files created or modified, commands run and their outcome, conclusions reached, questions asked and still unanswered. Include failures and abandoned attempts — those are the part a returning user is most likely to have missed.
Also worth knowing
Significant changes from earlier in the session that are still relevant: decisions made, approaches reversed, work left unfinished, anything agreed to but not yet done. Skip this section entirely if the session holds nothing beyond what the previous section already covered.
Rules
- Be brief. This is a status readout, not a transcript.
- Never invent timestamps, file names, or outcomes. Unknown is an acceptable answer.
- Distinguish what was done from what was only proposed.
- If the session has no prior user message, say that this is the first turn 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.
- yesterday First seen · 52 lines · 90 tokens per session scan A 0c37cd66237d
amnesia is a skill published in the GitHub repository Heapy/kortex (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 90 tokens to every session and 448 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 2026-08-31.
Other skills, from other repositories
mobile-experience-report
Use when the user says 'my site looks bad on mobile', 'check mobile layout', 'responsive audit', or 'site broken on phones'. Diagnoses breakpoint problems, text sizing, column stacking failures, hidden elements, and navigation menu behavior, device by device.
motherduck-design-dive
Design or redesign a MotherDuck Dive as a responsive, reusable analytics interface. Use when a Dive must be mobile-friendly from the start, support light and dark modes, reserve space for filters, use restrained Power BI-style information design, embed small charts inside metric components, or work across customers…
gradle-expert
Build optimization, dependency resolution, and multi-module KMP troubleshooting for AmethystMultiplatform. Use when working with: (1) Gradle build files (build.gradle.kts, settings.gradle), (2) Version catalog (libs.versions.toml), (3) Build errors and dependency conflicts, (4) Module dependencies and source sets, (5)…
add-native
Public entry point for native device capabilities and native controls — camera, image picker, barcode/QR scanner, document picker, file picker, secure storage, file system, sharing, PDF generation/viewing, pen/signature capture, background GPS/geolocation tracking, or supported local file workflows — in a Power Apps…
amy-expert
Patterns for extending amy, the Amethyst CLI in cli/. Use when adding an amy command, touching files under cli/src/main/kotlin/…/cli/, wiring a new subcommand into Main.kt, writing an interop test script that drives Amy, or extracting logic out of amethyst/ into commons/ so a CLI command can call it. Enforces the…
compose-side-effects
Use when writing or reviewing Jetpack Compose code with LaunchedEffect, DisposableEffect, SideEffect, rememberCoroutineScope, rememberUpdatedState, snapshotFlow, snackbar, navigation, focus requests, analytics, or event Flow collection. Technique-layer skill — complements the codebase-specific compose-expert.