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 catcatcatstudio/cat-skills --skill mementogit clone --depth 1 https://github.com/catcatcatstudio/cat-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/catcatcatstudio/cat-skills/memento)<a href="https://agentmods.dev/skills/catcatcatstudio/cat-skills/memento"><img src="https://agentmods.dev/badge/skills/catcatcatstudio/cat-skills/memento/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/catcatcatstudio/cat-skills/memento"><img src="https://agentmods.dev/badge/skills/catcatcatstudio/cat-skills/memento.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 | $0.00078 | $0.01853 |
| Opus 5 | $0.00039 | $0.00927 |
| Sonnet 5 | $0.00016 | $0.00371 |
| Haiku 4.5 | $0.00008 | $0.00185 |
Grade B, and why
memento scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Setup** — add to `~/.claude/settings.json`: How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memento
Save what matters, then produce a handoff for the next chat.
Commands
| Command | Action |
|---|---|
/memento |
Notebook triage + generate handoff |
/memento auto |
Show whether auto-compaction safety net is on or off |
/memento auto on |
Enable auto mode (preserves context across compaction) |
/memento auto off |
Disable auto mode |
/memento auto
The auto-compaction safety net is controlled by a flag file at ~/.claude/.memento-auto.
/memento auto— check if~/.claude/.memento-autoexists. Report:Memento auto: onorMemento auto: off. One line, nothing else./memento auto on— create~/.claude/.memento-auto(touch). Report:Memento auto: on. If hooks aren't configured yet, show the setup block from the Auto-Compaction section below./memento auto off— remove~/.claude/.memento-auto. Report:Memento auto: off.
What this does
Two things, in order:
-
Persist — scan the conversation for unsaved decisions, learnings, constraints, or failures. Save each one via /notebook save. This is the durable part — it survives regardless of whether the user pastes anything.
-
Orient — produce a short text block that gives a blank chat enough context to pick up where this one left off. This is the ephemeral part — it captures working state that's too in-the-moment for a notebook note.
Execution
Phase 1: Notebook Triage
Before generating the handoff, assess whether this session has unsaved knowledge.
Check signals:
- Have any /notebook save calls happened this session? How recently?
- Have decisions been made, constraints discovered, bugs hit, or approaches changed since the last save (or since session start if no saves)?
- Is there a _notebook/ at all? If not, the entire session is unsaved.
Decision:
- Session is well-persisted (recent notebook saves cover the important stuff) → skip to Phase 2. Say:
Notebook is current — skipping to handoff. - Session has unsaved knowledge → save each unsaved decision, constraint, learning, or failure via
/notebook save(delegate fully — follow notebook's save protocol for type inference, note format, index and lessons updates). If no notebook exists yet, initialize it first. - Session was trivial (no meaningful decisions or learnings, just exploration or small edits) → skip saves. Don't manufacture notes.
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 · 174 lines · 78 tokens per session scan B b5fd97c62279
memento is a skill published in the GitHub repository catcatcatstudio/cat-skills (3 stars, last pushed 14d ago), licensed MIT. It adds 78 tokens to every session and 1,853 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
assigns-audit
Inspect LiveView socket assigns for memory bloat — missing temporaryassigns, unused assigns, unbounded lists needing streams, memory estimates. Use when LiveView memory grows or you need to add temporaryassigns.
recall
Recall prior work from past sessions — how a bug was fixed, what was decided, where a pattern lives. Use when asked 'have we done this before' or 'how did I fix X' in Elixir/Phoenix work. ccrider MCP when available, else git + solution docs.
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
context-anchoring
Manage per-feature living documents that capture decisions, constraints, and reasoning across AI sessions during active development. Scoped to feature-level work — design, implementation, bugfix, refactor — not for codebase-wide assessments or product-wide specifications (those define their own document lifecycles).…
learning-harvest
Manage the operational learnings lifecycle — load prior learnings to inform current work, harvest new patterns worth preserving, and keep the document tight over time. Provides a protocol for accumulating actionable patterns from practice that complement standards and defaults. Use when a workflow session completes…