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 LucasSantana-Dev/sharekit --skill memory-prunegit clone --depth 1 https://github.com/LucasSantana-Dev/sharekitWrote 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/lucassantana-dev/sharekit/memory-prune)<a href="https://agentmods.dev/skills/lucassantana-dev/sharekit/memory-prune"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/memory-prune/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/lucassantana-dev/sharekit/memory-prune"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/memory-prune.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 | $0.00080 | $0.02029 |
| Opus 5.5 | $0.00032 | $0.00812 |
| Sonnet 5.5 | $0.00016 | $0.00406 |
| Haiku 4.5 | $0.00008 | $0.00203 |
Grade A, and why
memory-prune 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 1mo 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memory-prune
Project memory files at ~/.claude/projects/<encoded-cwd>/memory/*.md accumulate feedback_* and project_* notes faster than they decay. Entries cite PRs that have merged, branches that have been deleted, gotchas that have been patched. Future sessions follow them as if they were still current and waste effort re-discovering they're not.
This skill audits the memory dir, classifies each entry, and proposes archival.
When NOT to run
- Memory dir has <10 files → noise budget is low; not worth auditing.
- All entries are <30 days old → too soon to expire anything.
- A
memory-pruneaudit ran in the last 30 days and was acted on → nothing has aged out yet. - The user is mid-task → don't archive entries you might cite minutes later.
Inputs
- Memory dir (auto-detected from
$PWD):~/.claude/projects/$(pwd | tr '/' '-' | sed 's/^-//' | sed 's/^/-/' )/memory/ - MEMORY.md index (in same dir): the human-readable index that points at each file
- Repo for cite-validation (auto-detected from
gh repo view): used to query PR / branch / commit state
Classification rules
For each *.md file in the memory dir, read its frontmatter + body and classify:
| Verdict | Trigger | Action |
|---|---|---|
| archive | Cited PR is MERGED AND the gotcha was patched as part of that PR |
Move to memory/archive/<YYYY-MM-DD>-<file>.md |
| archive | Cited branch no longer exists on origin | Move to archive |
| archive | Cited file:line points to a file that no longer exists | Move to archive |
| archive | Cited PR is MERGED AND entry is type: project (status update, not a durable lesson) |
Move to archive |
| keep | type: feedback — durable lessons (gotchas, patterns) survive PR merges |
Keep |
| keep | type: reference — pointers to external resources |
Keep unless URL 404s |
| keep | type: user — identity/role; never expire |
Keep |
| update | type: project PR is MERGED but the entry still says "open" / "WIP" |
Edit to mark merged + add merge SHA, then keep |
| flag-for-user | Ambiguous — cited evidence partially resolved, partially open | List for manual review |
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.
- 1mo ago First seen · 185 lines · 80 tokens per session scan A 13972cf5217d
memory-prune is a skill published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed 3d ago), licensed MIT. It adds 80 tokens to every session and 2,029 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
save-learning
Saves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from now on', 'never do Y', or gives any instruction they want persisted across sessions. Proactively suggest when the user states a preference, convention, or rule they clearly want followed in…
sivtr-memory
Retrieve shared local work memory: terminal activity, AI conversation history, prior decisions, validation evidence, debugging trails, recaps, and handoff context. Use before asking the user to repeat local work context.
getnote-kb
A skill for reading and managing GetNote Brain, a knowledge-base service for books, customer records, team information, folders, notes, and subscribed creators or livestreams.