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 definite-d/agent-skills --skill amnesiagit clone --depth 1 https://github.com/definite-d/agent-skillsWrote 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/definite-d/agent-skills/amnesia)<a href="https://agentmods.dev/skills/definite-d/agent-skills/amnesia"><img src="https://agentmods.dev/badge/skills/definite-d/agent-skills/amnesia.svg" alt="Measured on agentmods" 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 | $0.00205 | $0.01380 |
| Opus 5 | $0.00102 | $0.00690 |
| Sonnet 5 | $0.00041 | $0.00276 |
| Haiku 4.5 | $0.00020 | $0.00138 |
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 6d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amnesia — context-wipe-resistant autonomous work
The problem
Context windows get reset or compacted mid-task. Everything held only in working memory is lost:
decisions, partial plans, learned facts, the "what do I do next" state. amnesia fixes this by
treating the filesystem as external memory — state lives in three files on disk, and the agent
rehydrates from them on every resume.
Core principle
If it matters and is in your head only, it will be forgotten. Write it down before it matters.
Rule of thumb: write state before starting a risky/long step and after every meaningful step. When in doubt, write.
When to set up
Initialize the triad at the start of any task that is:
- multi-step (3+ steps) and autonomous ("I'll leave you to it", "work autonomously")
- likely to hit long compiles/builds, web fetches, or deep research (context heavy)
- explicitly flagged for resets ("your context will be reset", "maximize your context window")
- single-shot per-message work does NOT need this — skip for quick Q&A or one-command fixes
The state triad
Place the three files at the task root (the directory the agent owns). Use the templates in
assets/ for the initial structure.
| File | Purpose | Written when |
|---|---|---|
PROMPT.md |
Self-contained context brief — lets a fresh, cold agent resume without prior conversation | init + whenever key facts change |
PLAN.md |
Checkboxed task tracker with claimed states | every step completion |
HISTORY.md |
Append-only decision log: decisions, rationale, pitfalls, facts gathered | at every decision/finding |
Optionally add a context/ subdir for research dumps or probe outputs if PROMPT.md would bloat.
PROMPT.md rules
- Write it so a fresh context can execute cold: goal, constraints, exact commands, exact paths, key identifiers (function names, file:line, crate versions), current state, next actions.
- Include a short "Current state / next actions" section that is updated continuously.
- No conversational filler. Dense, terse, machine-parseable.
- Preserve exact file paths, commands, version pins, and identifiers verbatim — fuzzy memory of a command line or flag costs a full re-discovery cycle.
What ships with it
4 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.
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.
- 6d ago First seen · 107 lines · 205 tokens per session scan A 709188595bda
amnesia is a skill published in the GitHub repository definite-d/agent-skills (2 stars, last pushed 5d ago), licensed MIT. It adds 205 tokens to every session and 1,380 once invoked, about $0.0010 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.